diff --git a/examples/aishell/conf/train_asr_paraformer_conformer_12e_6d_2048_256.yaml b/examples/aishell/conf/train_asr_paraformer_conformer_12e_6d_2048_256.yaml new file mode 100644 index 000000000..94b7f6d14 --- /dev/null +++ b/examples/aishell/conf/train_asr_paraformer_conformer_12e_6d_2048_256.yaml @@ -0,0 +1,113 @@ + +# network architecture +model: funasr.cli.models.paraformer:Paraformer +model_conf: + ctc_weight: 0.3 + lsm_weight: 0.1 + length_normalized_loss: false + predictor_weight: 1.0 + sampling_ratio: 0.4 + use_1st_decoder_loss: true + + +# encoder related +encoder: conformer +encoder_conf: + output_size: 256 # dimension of attention + attention_heads: 4 + linear_units: 2048 # the number of units of position-wise feed forward + num_blocks: 12 # the number of encoder blocks + dropout_rate: 0.1 + positional_dropout_rate: 0.1 + attention_dropout_rate: 0.0 + input_layer: conv2d # encoder architecture type + normalize_before: true + pos_enc_layer_type: rel_pos + selfattention_layer_type: rel_selfattn + activation_type: swish + macaron_style: true + use_cnn_module: true + cnn_module_kernel: 15 + +# decoder related +decoder: paraformer_decoder_san +decoder_conf: + attention_heads: 4 + linear_units: 2048 + num_blocks: 6 + dropout_rate: 0.1 + positional_dropout_rate: 0.1 + self_attention_dropout_rate: 0.0 + src_attention_dropout_rate: 0.0 + +# frontend related +frontend: wav_frontend +frontend_conf: + fs: 16000 + window: hamming + n_mels: 80 + frame_length: 25 + frame_shift: 10 + lfr_m: 1 + lfr_n: 1 + + +train_conf: + accum_grad: 1 + grad_clip: 5 + max_epoch: 150 + val_scheduler_criterion: + - valid + - acc + best_model_criterion: + - - valid + - acc + - max + keep_nbest_models: 10 + log_interval: 50 + +optim: adam +optim_conf: + lr: 0.0005 +scheduler: warmuplr +scheduler_conf: + warmup_steps: 30000 + +specaug: specaug +specaug_conf: + apply_time_warp: true + time_warp_window: 5 + time_warp_mode: bicubic + apply_freq_mask: true + freq_mask_width_range: + - 0 + - 30 + num_freq_mask: 2 + apply_time_mask: true + time_mask_width_range: + - 0 + - 40 + num_time_mask: 2 + +predictor: cif_predictor +predictor_conf: + idim: 256 + threshold: 1.0 + l_order: 1 + r_order: 1 + tail_threshold: 0.45 + +dataset_conf: + data_names: speech,text + data_types: sound,text + shuffle: True + shuffle_conf: + shuffle_size: 2048 + sort_size: 500 + batch_conf: + batch_type: example + batch_size: 2 + num_workers: 8 + + +normalize: null \ No newline at end of file diff --git a/examples/aishell/run.sh b/examples/aishell/run.sh new file mode 100644 index 000000000..786691f67 --- /dev/null +++ b/examples/aishell/run.sh @@ -0,0 +1,9 @@ + +cmd="funasr_cli/cli/train_cli.py" + +python $cmd \ +--config-path "/Users/zhifu/funasr_github/test_local/funasr_cli_egs" \ +--config-name "config.yaml" \ ++token_list="/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt" \ ++train_data_set_list="/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl" \ ++output_dir="/nfs/zhifu.gzf/ckpt/funasr2/exp1" \ No newline at end of file diff --git a/examples/industrial_data_pretraining/paraformer-large/conf/finetune.yaml b/examples/industrial_data_pretraining/paraformer-large/conf/finetune.yaml new file mode 100644 index 000000000..880aad95e --- /dev/null +++ b/examples/industrial_data_pretraining/paraformer-large/conf/finetune.yaml @@ -0,0 +1,120 @@ + +# network architecture +model: funasr.cli.models.paraformer:Paraformer +model_conf: + ctc_weight: 0.0 + lsm_weight: 0.1 + length_normalized_loss: true + predictor_weight: 1.0 + predictor_bias: 1 + sampling_ratio: 0.75 + +# encoder +encoder: sanm +encoder_conf: + output_size: 512 + attention_heads: 4 + linear_units: 2048 + num_blocks: 50 + dropout_rate: 0.1 + positional_dropout_rate: 0.1 + attention_dropout_rate: 0.1 + input_layer: pe + pos_enc_class: SinusoidalPositionEncoder + normalize_before: true + kernel_size: 11 + sanm_shfit: 0 + selfattention_layer_type: sanm + +# decoder +decoder: paraformer_decoder_sanm +decoder_conf: + attention_heads: 4 + linear_units: 2048 + num_blocks: 16 + dropout_rate: 0.1 + positional_dropout_rate: 0.1 + self_attention_dropout_rate: 0.1 + src_attention_dropout_rate: 0.1 + att_layer_num: 16 + kernel_size: 11 + sanm_shfit: 0 + +predictor: cif_predictor_v2 +predictor_conf: + idim: 512 + threshold: 1.0 + l_order: 1 + r_order: 1 + tail_threshold: 0.45 + +# frontend related +frontend: wav_frontend +frontend_conf: + fs: 16000 + window: hamming + n_mels: 80 + frame_length: 25 + frame_shift: 10 + lfr_m: 7 + lfr_n: 6 + +specaug: specaug_lfr +specaug_conf: + apply_time_warp: false + time_warp_window: 5 + time_warp_mode: bicubic + apply_freq_mask: true + freq_mask_width_range: + - 0 + - 30 + lfr_rate: 6 + num_freq_mask: 1 + apply_time_mask: true + time_mask_width_range: + - 0 + - 12 + num_time_mask: 1 + +train_conf: + accum_grad: 1 + grad_clip: 5 + max_epoch: 150 + val_scheduler_criterion: + - valid + - acc + best_model_criterion: + - - valid + - acc + - max + keep_nbest_models: 10 + log_interval: 50 + +optim: adam +optim_conf: + lr: 0.0005 +scheduler: warmuplr +scheduler_conf: + warmup_steps: 30000 + + +dataset_conf: + data_names: speech,text + data_types: sound,text + shuffle: True + shuffle_conf: + shuffle_size: 2048 + sort_size: 500 + batch_conf: + batch_type: example + batch_size: 2 + num_workers: 8 + +split_with_space: true +input_size: 560 +ctc_conf: + dropout_rate: 0.0 + ctc_type: builtin + reduce: true + ignore_nan_grad: true +normalize: null \ No newline at end of file diff --git a/examples/industrial_data_pretraining/paraformer-large/run.sh b/examples/industrial_data_pretraining/paraformer-large/run.sh new file mode 100644 index 000000000..9b40b817b --- /dev/null +++ b/examples/industrial_data_pretraining/paraformer-large/run.sh @@ -0,0 +1,12 @@ + +cmd="funasr/cli/train_cli.py" + +python $cmd \ ++model_pretrain="/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \ ++token_list="/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt" \ ++train_data_set_list="/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl" \ ++output_dir="/Users/zhifu/Downloads/ckpt/funasr2/exp2" \ ++device="cpu" + +#--config-path "/Users/zhifu/funasr_github/examples/industrial_data_pretraining/paraformer-large/conf" \ +#--config-name "finetune.yaml" \ \ No newline at end of file diff --git a/funasr/cli/models/paraformer.py b/funasr/cli/models/paraformer.py index ee8c0b428..7ca80f5b7 100644 --- a/funasr/cli/models/paraformer.py +++ b/funasr/cli/models/paraformer.py @@ -193,6 +193,7 @@ class Paraformer(nn.Module): self.decoder.embed = None self.use_1st_decoder_loss = use_1st_decoder_loss + self.length_normalized_loss = length_normalized_loss def forward( self, @@ -302,6 +303,8 @@ class Paraformer(nn.Module): stats["loss"] = torch.clone(loss.detach()) # force_gatherable: to-device and to-tensor if scalar for DataParallel + if self.length_normalized_loss: + batch_size = (text_lengths + self.predictor_bias).sum() loss, stats, weight = force_gatherable((loss, stats, batch_size), loss.device) return loss, stats, weight diff --git a/funasr/cli/train_cli.py b/funasr/cli/train_cli.py index 54cd2e833..c62153e19 100644 --- a/funasr/cli/train_cli.py +++ b/funasr/cli/train_cli.py @@ -25,17 +25,25 @@ from funasr.utils.dynamic_import import dynamic_import import torch.distributed as dist from torch.nn.parallel import DistributedDataParallel as DDP from torch.distributed.fsdp import FullyShardedDataParallel as FSDP - +from funasr.utils.download_from_hub import download_model def preprocess_config(cfg: DictConfig): for key, value in cfg.items(): if value == 'None': cfg[key] = None +@hydra.main(config_name=None, version_base=None) +def main_hydra(kwargs: DictConfig): + import pdb; pdb.set_trace() + if kwargs.get("model_pretrain"): + kwargs = download_model(**kwargs) + + import pdb; + pdb.set_trace() + main(**kwargs) -@hydra.main() -def main(kwargs: DictConfig): +def main(**kwargs): # preprocess_config(kwargs) # import pdb; pdb.set_trace() # set random seed @@ -76,10 +84,10 @@ def main(kwargs: DictConfig): # init_param init_param = kwargs.get("init_param", None) if init_param is not None: - init_param = eval(init_param) + init_param = init_param if isinstance(init_param, Sequence): init_param = (init_param,) - logging.info("init_param is not None: ", init_param) + logging.info("init_param is not None: %s", init_param) for p in init_param: logging.info(f"Loading pretrained params from {p}") load_pretrained_model( @@ -99,7 +107,7 @@ def main(kwargs: DictConfig): freeze_param = eval(freeze_param) if isinstance(freeze_param, Sequence): freeze_param = (freeze_param,) - logging.info("freeze_param is not None: ", freeze_param) + logging.info("freeze_param is not None: %s", freeze_param) for t in freeze_param: for k, p in model.named_parameters(): if k.startswith(t + ".") or k == t: @@ -138,9 +146,15 @@ def main(kwargs: DictConfig): dataloader_tr = torch.utils.data.DataLoader(dataset_tr, collate_fn=dataset_tr.collator, batch_sampler=batch_sampler, - num_workers=kwargs.get("num_workers", 0), + num_workers=kwargs.get("dataset_conf").get("num_workers", 4), pin_memory=True) - + + if (use_ddp or use_fsdp) and dist.get_rank() == 0 or not (use_ddp or use_fsdp) and local_rank == 0: + os.makedirs(kwargs.get("output_dir", "./"), exist_ok=True) + yaml_file = os.path.join(kwargs.get("output_dir", "./"), "config.yaml") + OmegaConf.save(config=kwargs, f=yaml_file) + logging.info("config.yaml is saved to: %s", yaml_file) + trainer = Trainer( model=model, optim=optim, @@ -160,4 +174,4 @@ def main(kwargs: DictConfig): if __name__ == "__main__": - main() \ No newline at end of file + main_hydra() \ No newline at end of file diff --git a/funasr/cli/trainer.py b/funasr/cli/trainer.py index 28a843b87..01787673a 100644 --- a/funasr/cli/trainer.py +++ b/funasr/cli/trainer.py @@ -2,6 +2,7 @@ import torch import os from funasr.torch_utils.device_funcs import to_device import logging +import time from tqdm import tqdm from contextlib import nullcontext import torch.distributed as dist @@ -53,20 +54,28 @@ class Trainer: self.dataloader_train = dataloader_train self.dataloader_val = dataloader_val self.output_dir = kwargs.get('output_dir', './') - self.resume = kwargs.get('resume', None) + self.resume = kwargs.get('resume', True) self.start_epoch = 1 self.max_epoch = kwargs.get('max_epoch', 100) self.local_rank = local_rank - self.rank = dist.get_rank() - self.world_size = dist.get_world_size() self.use_ddp = use_ddp self.use_fsdp = use_fsdp - self.device = torch.device("cuda", local_rank) + self.device = next(model.parameters()).device self.kwargs = kwargs if self.resume: self._resume_checkpoint(self.resume) + try: + rank = dist.get_rank() + world_size = dist.get_world_size() + except: + rank = 0 + world_size = 1 + logging.warning("distributed is not initialized, only single shard") + self.rank = rank + self.world_size = world_size + def _save_checkpoint(self, epoch): """ Saves a checkpoint containing the model's state, the optimizer's state, @@ -117,6 +126,7 @@ class Trainer: if dist.get_rank() == 0: self._save_checkpoint(epoch) self.scheduler.step() + break def _train_epoch(self, epoch): """ @@ -132,13 +142,21 @@ class Trainer: accum_grad = self.kwargs.get("accum_grad", 1) # Initialize the gradient accumulation self.optim.zero_grad() - + speed_stats = {} + time5 = time.perf_counter() for batch_idx, batch in enumerate(self.dataloader_train): + time1 = time.perf_counter() + speed_stats["data_load"] = f"{time1-time5:0.3f}" + # import pdb; + # pdb.set_trace() batch = to_device(batch, self.device) my_context = self.model.no_sync if batch_idx % accum_grad != 0 else nullcontext with my_context(): + time2 = time.perf_counter() retval = self.model(**batch) + time3 = time.perf_counter() + speed_stats["forward_time"] = f"{time3 - time2:0.3f}" loss, stats, weight = retval stats = {k: v for k, v in stats.items() if v is not None} if self.use_ddp or self.use_fsdp: @@ -154,6 +172,8 @@ class Trainer: # Scale the loss since we're not updating for every mini-batch loss = loss / accum_grad loss.backward() + time4 = time.perf_counter() + speed_stats["backward_time"] = f"{time4 - time3:0.3f}" # Perform an optimizer step only after accumulating enough gradients if (batch_idx + 1) % accum_grad == 0 or (batch_idx + 1) == len(self.dataloader_train): @@ -176,12 +196,26 @@ class Trainer: self.scheduler.step() # Clear gradients for the next accumulation stage self.optim.zero_grad() + total_time = f"{time.perf_counter() - time5:0.3f}" + time5 = time.perf_counter() + speed_stats["optim_time"] = f"{time5 - time4:0.3f}" + + speed_stats["total_time"] = total_time + pbar.update(1) if self.local_rank == 0: - pbar.set_description( - f"Training Epoch: {epoch + 1}/{self.max_epoch}, step {batch_idx}/{len(self.dataloader_train)} (loss: {loss.detach().float():.3f}, {[(k, round(v.cpu().item(), 3)) for k, v in stats.items()]})") + description = ( + f"Epoch: {epoch + 1}/{self.max_epoch}, " + f"step {batch_idx}/{len(self.dataloader_train)}, " + f"{speed_stats}, " + f"(loss: {loss.detach().float():.3f}), " + f"{[(k, round(v.cpu().item(), 3)) for k, v in stats.items()]}" + ) + pbar.set_description(description) + if batch_idx == 2: + break pbar.close() def _validate_epoch(self, epoch): diff --git a/funasr/datasets/dataset_jsonl.py b/funasr/datasets/dataset_jsonl.py index eef67c5ee..7f2cd83d6 100644 --- a/funasr/datasets/dataset_jsonl.py +++ b/funasr/datasets/dataset_jsonl.py @@ -6,6 +6,7 @@ import kaldiio import librosa import torchaudio import time +import logging def load_audio(audio_path: str, fs: int=16000): audio = None @@ -41,8 +42,7 @@ class IndexedDatasetJsonl(torch.utils.data.Dataset): def __init__(self, path): super().__init__() - # data_parallel_size = dist.get_world_size() - data_parallel_size = 1 + contents = [] with open(path, encoding='utf-8') as fin: for line in fin: @@ -66,12 +66,20 @@ class IndexedDatasetJsonl(torch.utils.data.Dataset): self.contents = [] total_num = len(contents) - num_per_rank = total_num // data_parallel_size - # rank = dist.get_rank() - rank = 0 + try: + rank = dist.get_rank() + world_size = dist.get_world_size() + except: + rank = 0 + world_size = 1 + logging.warning("distributed is not initialized, only single shard") + num_per_rank = total_num // world_size + + # rank = 0 # import ipdb; ipdb.set_trace() self.contents = contents[rank * num_per_rank:(rank + 1) * num_per_rank] - + + logging.info("in rank: {}, num of samplers: {}, total_num of samplers across ranks: {}".format(rank, len(self.contents), len(contents))) def __len__(self): return len(self.contents) diff --git a/funasr/utils/download_from_hub.py b/funasr/utils/download_from_hub.py new file mode 100644 index 000000000..d6e4ab4e4 --- /dev/null +++ b/funasr/utils/download_from_hub.py @@ -0,0 +1,63 @@ +import os +from omegaconf import OmegaConf +import torch +from funasr.utils.name_maps_from_hub import name_maps_ms, name_maps_hf + +def download_model(**kwargs): + model_hub = kwargs.get("model_hub", "ms") + if model_hub == "ms": + kwargs = download_fr_ms(**kwargs) + + return kwargs + +def download_fr_ms(**kwargs): + model_or_path = kwargs.get("model_pretrain") + model_revision = kwargs.get("model_pretrain_revision") + if not os.path.exists(model_or_path): + model_or_path = get_or_download_model_dir(model_or_path, model_revision, third_party="funasr") + + config = os.path.join(model_or_path, "config.yaml") + assert os.path.exists(config), "{} is not exist!".format(config) + cfg = OmegaConf.load(config) + kwargs = OmegaConf.merge(cfg, kwargs) + init_param = os.path.join(model_or_path, "model.pb") + kwargs["init_param"] = init_param + kwargs["token_list"] = os.path.join(model_or_path, "tokens.txt") + + return kwargs + +def get_or_download_model_dir( + model, + model_revision=None, + third_party=None): + """ Get local model directory or download model if necessary. + + Args: + model (str): model id or path to local model directory. + model_revision (str, optional): model version number. + third_party (str, optional): in which third party library + this function is called. + """ + from modelscope.hub.check_model import check_local_model_is_latest + from modelscope.hub.snapshot_download import snapshot_download + + from modelscope.utils.constant import Invoke, ThirdParty + + if os.path.exists(model): + model_cache_dir = model if os.path.isdir( + model) else os.path.dirname(model) + check_local_model_is_latest( + model_cache_dir, + user_agent={ + Invoke.KEY: Invoke.LOCAL_TRAINER, + ThirdParty.KEY: third_party + }) + else: + model_cache_dir = snapshot_download( + model, + revision=model_revision, + user_agent={ + Invoke.KEY: Invoke.TRAINER, + ThirdParty.KEY: third_party + }) + return model_cache_dir \ No newline at end of file diff --git a/funasr/utils/name_maps_from_hub.py b/funasr/utils/name_maps_from_hub.py new file mode 100644 index 000000000..90b44cd43 --- /dev/null +++ b/funasr/utils/name_maps_from_hub.py @@ -0,0 +1,16 @@ + + +name_maps_ms = { + "paraformer-zh": "damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch", + "paraformer-zh-spk": "damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn", + "paraformer-en": "damo/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020", + "paraformer-en-spk": "damo/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020", + "paraformer-zh-streaming": "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online", + "fsmn-vad": "damo/speech_fsmn_vad_zh-cn-16k-common-pytorch", + "ct-punc": "damo/punc_ct-transformer_cn-en-common-vocab471067-large", + "fa-zh": "damo/speech_timestamp_prediction-v1-16k-offline", +} + +name_maps_hf = { + +} \ No newline at end of file diff --git a/outputs/2023-12-11/10-35-57/.hydra/config.yaml b/outputs/2023-12-11/10-35-57/.hydra/config.yaml new file mode 100644 index 000000000..0967ef424 --- /dev/null +++ b/outputs/2023-12-11/10-35-57/.hydra/config.yaml @@ -0,0 +1 @@ +{} diff --git a/outputs/2023-12-11/10-35-57/.hydra/hydra.yaml b/outputs/2023-12-11/10-35-57/.hydra/hydra.yaml new file mode 100644 index 000000000..3526e0f53 --- /dev/null +++ b/outputs/2023-12-11/10-35-57/.hydra/hydra.yaml @@ -0,0 +1,154 @@ +hydra: + run: + dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S} + sweep: + dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: [] + job: + name: train_cli + chdir: null + override_dirname: '' + id: ??? + num: ??? + config_name: null + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.3.2 + version_base: '1.1' + cwd: /Users/zhifu/funasr_github + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: /Users/zhifu/funasr_github/funasr/cli + schema: file + provider: main + - path: '' + schema: structured + provider: schema + output_dir: /Users/zhifu/funasr_github/outputs/2023-12-11/10-35-57 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/outputs/2023-12-11/10-35-57/.hydra/overrides.yaml b/outputs/2023-12-11/10-35-57/.hydra/overrides.yaml new file mode 100644 index 000000000..fe51488c7 --- /dev/null +++ b/outputs/2023-12-11/10-35-57/.hydra/overrides.yaml @@ -0,0 +1 @@ +[] diff --git a/outputs/2023-12-11/10-35-57/train_cli.log b/outputs/2023-12-11/10-35-57/train_cli.log new file mode 100644 index 000000000..e69de29bb diff --git a/outputs/2023-12-11/10-37-01/.hydra/config.yaml b/outputs/2023-12-11/10-37-01/.hydra/config.yaml new file mode 100644 index 000000000..0967ef424 --- /dev/null +++ b/outputs/2023-12-11/10-37-01/.hydra/config.yaml @@ -0,0 +1 @@ +{} diff --git a/outputs/2023-12-11/10-37-01/.hydra/hydra.yaml b/outputs/2023-12-11/10-37-01/.hydra/hydra.yaml new file mode 100644 index 000000000..1f352f25c --- /dev/null +++ b/outputs/2023-12-11/10-37-01/.hydra/hydra.yaml @@ -0,0 +1,154 @@ +hydra: + run: + dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S} + sweep: + dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: [] + job: + name: train_cli + chdir: null + override_dirname: '' + id: ??? + num: ??? + config_name: null + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.3.2 + version_base: '1.1' + cwd: /Users/zhifu/funasr_github + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: /Users/zhifu/funasr_github/funasr/cli + schema: file + provider: main + - path: '' + schema: structured + provider: schema + output_dir: /Users/zhifu/funasr_github/outputs/2023-12-11/10-37-01 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/outputs/2023-12-11/10-37-01/.hydra/overrides.yaml b/outputs/2023-12-11/10-37-01/.hydra/overrides.yaml new file mode 100644 index 000000000..fe51488c7 --- /dev/null +++ b/outputs/2023-12-11/10-37-01/.hydra/overrides.yaml @@ -0,0 +1 @@ +[] diff --git a/outputs/2023-12-11/10-37-01/train_cli.log b/outputs/2023-12-11/10-37-01/train_cli.log new file mode 100644 index 000000000..e69de29bb diff --git a/outputs/2023-12-11/10-39-53/.hydra/config.yaml b/outputs/2023-12-11/10-39-53/.hydra/config.yaml new file mode 100644 index 000000000..0967ef424 --- /dev/null +++ b/outputs/2023-12-11/10-39-53/.hydra/config.yaml @@ -0,0 +1 @@ +{} diff --git a/outputs/2023-12-11/10-39-53/.hydra/hydra.yaml b/outputs/2023-12-11/10-39-53/.hydra/hydra.yaml new file mode 100644 index 000000000..2be084259 --- /dev/null +++ b/outputs/2023-12-11/10-39-53/.hydra/hydra.yaml @@ -0,0 +1,154 @@ +hydra: + run: + dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S} + sweep: + dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: [] + job: + name: train_cli + chdir: null + override_dirname: '' + id: ??? + num: ??? + config_name: null + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.3.2 + version_base: '1.1' + cwd: /Users/zhifu/funasr_github + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: /Users/zhifu/funasr_github/funasr/cli + schema: file + provider: main + - path: '' + schema: structured + provider: schema + output_dir: /Users/zhifu/funasr_github/outputs/2023-12-11/10-39-53 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/outputs/2023-12-11/10-39-53/.hydra/overrides.yaml b/outputs/2023-12-11/10-39-53/.hydra/overrides.yaml new file mode 100644 index 000000000..fe51488c7 --- /dev/null +++ b/outputs/2023-12-11/10-39-53/.hydra/overrides.yaml @@ -0,0 +1 @@ +[] diff --git a/outputs/2023-12-11/10-39-53/train_cli.log b/outputs/2023-12-11/10-39-53/train_cli.log new file mode 100644 index 000000000..e69de29bb diff --git a/outputs/2023-12-11/10-41-29/.hydra/config.yaml b/outputs/2023-12-11/10-41-29/.hydra/config.yaml new file mode 100644 index 000000000..5af8fee75 --- /dev/null +++ b/outputs/2023-12-11/10-41-29/.hydra/config.yaml @@ -0,0 +1,74 @@ +model: funasr.cli.models.paraformer:Paraformer +model_conf: + ctc_weight: 0.3 + lsm_weight: 0.1 + length_normalized_loss: false + predictor_weight: 1.0 + sampling_ratio: 0.4 + use_1st_decoder_loss: true +frontend: wav_frontend +frontend_conf: + fs: 16000 + window: hamming + n_mels: 80 + frame_length: 25 + frame_shift: 10 + lfr_m: 1 + lfr_n: 1 +train_conf: + accum_grad: 1 + grad_clip: 5 + max_epoch: 150 + val_scheduler_criterion: + - valid + - acc + best_model_criterion: + - - valid + - acc + - max + keep_nbest_models: 10 + log_interval: 50 +optim: adam +optim_conf: + lr: 0.0005 +scheduler: warmuplr +scheduler_conf: + warmup_steps: 30000 +specaug: specaug +specaug_conf: + apply_time_warp: true + time_warp_window: 5 + time_warp_mode: bicubic + apply_freq_mask: true + freq_mask_width_range: + - 0 + - 30 + num_freq_mask: 2 + apply_time_mask: true + time_mask_width_range: + - 0 + - 40 + num_time_mask: 2 +predictor: cif_predictor +predictor_conf: + idim: 256 + threshold: 1.0 + l_order: 1 + r_order: 1 + tail_threshold: 0.45 +dataset_conf: + data_names: speech,text + data_types: sound,text + shuffle: true + shuffle_conf: + shuffle_size: 2048 + sort_size: 500 + batch_conf: + batch_type: example + batch_size: 2 + num_workers: 8 +normalize: null +model_pretrain: damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch +token_list: /Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +train_data_set_list: /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +output_dir: /nfs/zhifu.gzf/ckpt/funasr2/exp2 diff --git a/outputs/2023-12-11/10-41-29/.hydra/hydra.yaml b/outputs/2023-12-11/10-41-29/.hydra/hydra.yaml new file mode 100644 index 000000000..66deec6ef --- /dev/null +++ b/outputs/2023-12-11/10-41-29/.hydra/hydra.yaml @@ -0,0 +1,158 @@ +hydra: + run: + dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S} + sweep: + dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - +model_pretrain=damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch + - +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt + - +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + - +output_dir=/nfs/zhifu.gzf/ckpt/funasr2/exp2 + job: + name: train_cli + chdir: null + override_dirname: +model_pretrain=damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch,+output_dir=/nfs/zhifu.gzf/ckpt/funasr2/exp2,+token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt,+train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + id: ??? + num: ??? + config_name: finetune.yaml + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.3.2 + version_base: '1.1' + cwd: /Users/zhifu/funasr_github + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: /Users/zhifu/funasr_github/examples/industrial_data_pretraining/paraformer-large/conf + schema: file + provider: main + - path: '' + schema: structured + provider: schema + output_dir: /Users/zhifu/funasr_github/outputs/2023-12-11/10-41-29 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/outputs/2023-12-11/10-41-29/.hydra/overrides.yaml b/outputs/2023-12-11/10-41-29/.hydra/overrides.yaml new file mode 100644 index 000000000..d8138454e --- /dev/null +++ b/outputs/2023-12-11/10-41-29/.hydra/overrides.yaml @@ -0,0 +1,4 @@ +- +model_pretrain=damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch +- +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +- +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +- +output_dir=/nfs/zhifu.gzf/ckpt/funasr2/exp2 diff --git a/outputs/2023-12-11/10-41-29/train_cli.log b/outputs/2023-12-11/10-41-29/train_cli.log new file mode 100644 index 000000000..e69de29bb diff --git a/outputs/2023-12-11/10-44-08/.hydra/config.yaml b/outputs/2023-12-11/10-44-08/.hydra/config.yaml new file mode 100644 index 000000000..380db4264 --- /dev/null +++ b/outputs/2023-12-11/10-44-08/.hydra/config.yaml @@ -0,0 +1,4 @@ +model_pretrain: damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch +token_list: /Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +train_data_set_list: /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +output_dir: /nfs/zhifu.gzf/ckpt/funasr2/exp2 diff --git a/outputs/2023-12-11/10-44-08/.hydra/hydra.yaml b/outputs/2023-12-11/10-44-08/.hydra/hydra.yaml new file mode 100644 index 000000000..fd886551b --- /dev/null +++ b/outputs/2023-12-11/10-44-08/.hydra/hydra.yaml @@ -0,0 +1,158 @@ +hydra: + run: + dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S} + sweep: + dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - +model_pretrain=damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch + - +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt + - +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + - +output_dir=/nfs/zhifu.gzf/ckpt/funasr2/exp2 + job: + name: train_cli + chdir: null + override_dirname: +model_pretrain=damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch,+output_dir=/nfs/zhifu.gzf/ckpt/funasr2/exp2,+token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt,+train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + id: ??? + num: ??? + config_name: null + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.3.2 + version_base: '1.1' + cwd: /Users/zhifu/funasr_github + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: /Users/zhifu/funasr_github/funasr/cli + schema: file + provider: main + - path: '' + schema: structured + provider: schema + output_dir: /Users/zhifu/funasr_github/outputs/2023-12-11/10-44-08 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/outputs/2023-12-11/10-44-08/.hydra/overrides.yaml b/outputs/2023-12-11/10-44-08/.hydra/overrides.yaml new file mode 100644 index 000000000..d8138454e --- /dev/null +++ b/outputs/2023-12-11/10-44-08/.hydra/overrides.yaml @@ -0,0 +1,4 @@ +- +model_pretrain=damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch +- +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +- +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +- +output_dir=/nfs/zhifu.gzf/ckpt/funasr2/exp2 diff --git a/outputs/2023-12-11/10-44-08/train_cli.log b/outputs/2023-12-11/10-44-08/train_cli.log new file mode 100644 index 000000000..e69de29bb diff --git a/outputs/2023-12-11/10-45-48/.hydra/config.yaml b/outputs/2023-12-11/10-45-48/.hydra/config.yaml new file mode 100644 index 000000000..380db4264 --- /dev/null +++ b/outputs/2023-12-11/10-45-48/.hydra/config.yaml @@ -0,0 +1,4 @@ +model_pretrain: damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch +token_list: /Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +train_data_set_list: /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +output_dir: /nfs/zhifu.gzf/ckpt/funasr2/exp2 diff --git a/outputs/2023-12-11/10-45-48/.hydra/hydra.yaml b/outputs/2023-12-11/10-45-48/.hydra/hydra.yaml new file mode 100644 index 000000000..8d4d4f5ae --- /dev/null +++ b/outputs/2023-12-11/10-45-48/.hydra/hydra.yaml @@ -0,0 +1,158 @@ +hydra: + run: + dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S} + sweep: + dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - +model_pretrain=damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch + - +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt + - +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + - +output_dir=/nfs/zhifu.gzf/ckpt/funasr2/exp2 + job: + name: train_cli + chdir: null + override_dirname: +model_pretrain=damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch,+output_dir=/nfs/zhifu.gzf/ckpt/funasr2/exp2,+token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt,+train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + id: ??? + num: ??? + config_name: null + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.3.2 + version_base: '1.1' + cwd: /Users/zhifu/funasr_github + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: /Users/zhifu/funasr_github/funasr/cli + schema: file + provider: main + - path: '' + schema: structured + provider: schema + output_dir: /Users/zhifu/funasr_github/outputs/2023-12-11/10-45-48 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/outputs/2023-12-11/10-45-48/.hydra/overrides.yaml b/outputs/2023-12-11/10-45-48/.hydra/overrides.yaml new file mode 100644 index 000000000..d8138454e --- /dev/null +++ b/outputs/2023-12-11/10-45-48/.hydra/overrides.yaml @@ -0,0 +1,4 @@ +- +model_pretrain=damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch +- +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +- +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +- +output_dir=/nfs/zhifu.gzf/ckpt/funasr2/exp2 diff --git a/outputs/2023-12-11/10-45-48/train_cli.log b/outputs/2023-12-11/10-45-48/train_cli.log new file mode 100644 index 000000000..e69de29bb diff --git a/outputs/2023-12-11/11-26-16/.hydra/config.yaml b/outputs/2023-12-11/11-26-16/.hydra/config.yaml new file mode 100644 index 000000000..10ea67677 --- /dev/null +++ b/outputs/2023-12-11/11-26-16/.hydra/config.yaml @@ -0,0 +1,4 @@ +model_pretrain: /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +token_list: /Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +train_data_set_list: /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +output_dir: /nfs/zhifu.gzf/ckpt/funasr2/exp2 diff --git a/outputs/2023-12-11/11-26-16/.hydra/hydra.yaml b/outputs/2023-12-11/11-26-16/.hydra/hydra.yaml new file mode 100644 index 000000000..e3c206ba3 --- /dev/null +++ b/outputs/2023-12-11/11-26-16/.hydra/hydra.yaml @@ -0,0 +1,158 @@ +hydra: + run: + dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S} + sweep: + dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch + - +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt + - +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + - +output_dir=/nfs/zhifu.gzf/ckpt/funasr2/exp2 + job: + name: train_cli + chdir: null + override_dirname: +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch,+output_dir=/nfs/zhifu.gzf/ckpt/funasr2/exp2,+token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt,+train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + id: ??? + num: ??? + config_name: null + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.3.2 + version_base: '1.1' + cwd: /Users/zhifu/funasr_github + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: /Users/zhifu/funasr_github/funasr/cli + schema: file + provider: main + - path: '' + schema: structured + provider: schema + output_dir: /Users/zhifu/funasr_github/outputs/2023-12-11/11-26-16 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/outputs/2023-12-11/11-26-16/.hydra/overrides.yaml b/outputs/2023-12-11/11-26-16/.hydra/overrides.yaml new file mode 100644 index 000000000..95db59363 --- /dev/null +++ b/outputs/2023-12-11/11-26-16/.hydra/overrides.yaml @@ -0,0 +1,4 @@ +- +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +- +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +- +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +- +output_dir=/nfs/zhifu.gzf/ckpt/funasr2/exp2 diff --git a/outputs/2023-12-11/11-26-16/train_cli.log b/outputs/2023-12-11/11-26-16/train_cli.log new file mode 100644 index 000000000..e69de29bb diff --git a/outputs/2023-12-11/11-32-18/.hydra/config.yaml b/outputs/2023-12-11/11-32-18/.hydra/config.yaml new file mode 100644 index 000000000..10ea67677 --- /dev/null +++ b/outputs/2023-12-11/11-32-18/.hydra/config.yaml @@ -0,0 +1,4 @@ +model_pretrain: /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +token_list: /Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +train_data_set_list: /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +output_dir: /nfs/zhifu.gzf/ckpt/funasr2/exp2 diff --git a/outputs/2023-12-11/11-32-18/.hydra/hydra.yaml b/outputs/2023-12-11/11-32-18/.hydra/hydra.yaml new file mode 100644 index 000000000..b9ddf5b4d --- /dev/null +++ b/outputs/2023-12-11/11-32-18/.hydra/hydra.yaml @@ -0,0 +1,155 @@ +hydra: + run: + dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S} + sweep: + dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch + - +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt + - +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + - +output_dir=/nfs/zhifu.gzf/ckpt/funasr2/exp2 + job: + name: train_cli + chdir: null + override_dirname: +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch,+output_dir=/nfs/zhifu.gzf/ckpt/funasr2/exp2,+token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt,+train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + id: ??? + num: ??? + config_name: null + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.3.2 + version_base: '1.3' + cwd: /Users/zhifu/funasr_github + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: '' + schema: structured + provider: schema + output_dir: /Users/zhifu/funasr_github/outputs/2023-12-11/11-32-18 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/outputs/2023-12-11/11-32-18/.hydra/overrides.yaml b/outputs/2023-12-11/11-32-18/.hydra/overrides.yaml new file mode 100644 index 000000000..95db59363 --- /dev/null +++ b/outputs/2023-12-11/11-32-18/.hydra/overrides.yaml @@ -0,0 +1,4 @@ +- +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +- +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +- +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +- +output_dir=/nfs/zhifu.gzf/ckpt/funasr2/exp2 diff --git a/outputs/2023-12-11/11-32-18/train_cli.log b/outputs/2023-12-11/11-32-18/train_cli.log new file mode 100644 index 000000000..9dca346e9 --- /dev/null +++ b/outputs/2023-12-11/11-32-18/train_cli.log @@ -0,0 +1 @@ +[2023-12-11 11:32:54,061][root][INFO] - Loading pretrained params from /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.pb diff --git a/outputs/2023-12-11/11-33-27/.hydra/config.yaml b/outputs/2023-12-11/11-33-27/.hydra/config.yaml new file mode 100644 index 000000000..2cd56325f --- /dev/null +++ b/outputs/2023-12-11/11-33-27/.hydra/config.yaml @@ -0,0 +1,5 @@ +model_pretrain: /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +token_list: /Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +train_data_set_list: /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +output_dir: /nfs/zhifu.gzf/ckpt/funasr2/exp2 +device: cpu diff --git a/outputs/2023-12-11/11-33-27/.hydra/hydra.yaml b/outputs/2023-12-11/11-33-27/.hydra/hydra.yaml new file mode 100644 index 000000000..67e44bf75 --- /dev/null +++ b/outputs/2023-12-11/11-33-27/.hydra/hydra.yaml @@ -0,0 +1,156 @@ +hydra: + run: + dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S} + sweep: + dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch + - +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt + - +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + - +output_dir=/nfs/zhifu.gzf/ckpt/funasr2/exp2 + - +device=cpu + job: + name: train_cli + chdir: null + override_dirname: +device=cpu,+model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch,+output_dir=/nfs/zhifu.gzf/ckpt/funasr2/exp2,+token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt,+train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + id: ??? + num: ??? + config_name: null + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.3.2 + version_base: '1.3' + cwd: /Users/zhifu/funasr_github + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: '' + schema: structured + provider: schema + output_dir: /Users/zhifu/funasr_github/outputs/2023-12-11/11-33-27 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/outputs/2023-12-11/11-33-27/.hydra/overrides.yaml b/outputs/2023-12-11/11-33-27/.hydra/overrides.yaml new file mode 100644 index 000000000..133750121 --- /dev/null +++ b/outputs/2023-12-11/11-33-27/.hydra/overrides.yaml @@ -0,0 +1,5 @@ +- +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +- +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +- +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +- +output_dir=/nfs/zhifu.gzf/ckpt/funasr2/exp2 +- +device=cpu diff --git a/outputs/2023-12-11/11-33-27/train_cli.log b/outputs/2023-12-11/11-33-27/train_cli.log new file mode 100644 index 000000000..9fabe158c --- /dev/null +++ b/outputs/2023-12-11/11-33-27/train_cli.log @@ -0,0 +1 @@ +[2023-12-11 11:33:45,313][root][INFO] - Loading pretrained params from /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.pb diff --git a/outputs/2023-12-11/11-36-25/.hydra/config.yaml b/outputs/2023-12-11/11-36-25/.hydra/config.yaml new file mode 100644 index 000000000..2cd56325f --- /dev/null +++ b/outputs/2023-12-11/11-36-25/.hydra/config.yaml @@ -0,0 +1,5 @@ +model_pretrain: /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +token_list: /Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +train_data_set_list: /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +output_dir: /nfs/zhifu.gzf/ckpt/funasr2/exp2 +device: cpu diff --git a/outputs/2023-12-11/11-36-25/.hydra/hydra.yaml b/outputs/2023-12-11/11-36-25/.hydra/hydra.yaml new file mode 100644 index 000000000..c4cf67fed --- /dev/null +++ b/outputs/2023-12-11/11-36-25/.hydra/hydra.yaml @@ -0,0 +1,156 @@ +hydra: + run: + dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S} + sweep: + dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch + - +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt + - +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + - +output_dir=/nfs/zhifu.gzf/ckpt/funasr2/exp2 + - +device=cpu + job: + name: train_cli + chdir: null + override_dirname: +device=cpu,+model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch,+output_dir=/nfs/zhifu.gzf/ckpt/funasr2/exp2,+token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt,+train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + id: ??? + num: ??? + config_name: null + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.3.2 + version_base: '1.3' + cwd: /Users/zhifu/funasr_github + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: '' + schema: structured + provider: schema + output_dir: /Users/zhifu/funasr_github/outputs/2023-12-11/11-36-25 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/outputs/2023-12-11/11-36-25/.hydra/overrides.yaml b/outputs/2023-12-11/11-36-25/.hydra/overrides.yaml new file mode 100644 index 000000000..133750121 --- /dev/null +++ b/outputs/2023-12-11/11-36-25/.hydra/overrides.yaml @@ -0,0 +1,5 @@ +- +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +- +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +- +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +- +output_dir=/nfs/zhifu.gzf/ckpt/funasr2/exp2 +- +device=cpu diff --git a/outputs/2023-12-11/11-36-25/train_cli.log b/outputs/2023-12-11/11-36-25/train_cli.log new file mode 100644 index 000000000..cf0585deb --- /dev/null +++ b/outputs/2023-12-11/11-36-25/train_cli.log @@ -0,0 +1,2 @@ +[2023-12-11 11:36:30,624][root][INFO] - Loading pretrained params from /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.pb +[2023-12-11 11:36:31,819][root][WARNING] - distributed is not initialized, only single shard diff --git a/outputs/2023-12-11/11-37-13/.hydra/config.yaml b/outputs/2023-12-11/11-37-13/.hydra/config.yaml new file mode 100644 index 000000000..2f5101274 --- /dev/null +++ b/outputs/2023-12-11/11-37-13/.hydra/config.yaml @@ -0,0 +1,5 @@ +model_pretrain: /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +token_list: /Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +train_data_set_list: /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +output_dir: /Users/zhifu.gzf/ckpt/funasr2/exp2 +device: cpu diff --git a/outputs/2023-12-11/11-37-13/.hydra/hydra.yaml b/outputs/2023-12-11/11-37-13/.hydra/hydra.yaml new file mode 100644 index 000000000..aaaf4c2be --- /dev/null +++ b/outputs/2023-12-11/11-37-13/.hydra/hydra.yaml @@ -0,0 +1,156 @@ +hydra: + run: + dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S} + sweep: + dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch + - +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt + - +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + - +output_dir=/Users/zhifu.gzf/ckpt/funasr2/exp2 + - +device=cpu + job: + name: train_cli + chdir: null + override_dirname: +device=cpu,+model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch,+output_dir=/Users/zhifu.gzf/ckpt/funasr2/exp2,+token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt,+train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + id: ??? + num: ??? + config_name: null + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.3.2 + version_base: '1.3' + cwd: /Users/zhifu/funasr_github + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: '' + schema: structured + provider: schema + output_dir: /Users/zhifu/funasr_github/outputs/2023-12-11/11-37-13 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/outputs/2023-12-11/11-37-13/.hydra/overrides.yaml b/outputs/2023-12-11/11-37-13/.hydra/overrides.yaml new file mode 100644 index 000000000..7a670758c --- /dev/null +++ b/outputs/2023-12-11/11-37-13/.hydra/overrides.yaml @@ -0,0 +1,5 @@ +- +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +- +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +- +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +- +output_dir=/Users/zhifu.gzf/ckpt/funasr2/exp2 +- +device=cpu diff --git a/outputs/2023-12-11/11-37-13/train_cli.log b/outputs/2023-12-11/11-37-13/train_cli.log new file mode 100644 index 000000000..0d78f1b4a --- /dev/null +++ b/outputs/2023-12-11/11-37-13/train_cli.log @@ -0,0 +1,2 @@ +[2023-12-11 11:43:26,900][root][INFO] - Loading pretrained params from /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.pb +[2023-12-11 11:43:28,209][root][WARNING] - distributed is not initialized, only single shard diff --git a/outputs/2023-12-11/11-44-36/.hydra/config.yaml b/outputs/2023-12-11/11-44-36/.hydra/config.yaml new file mode 100644 index 000000000..85ff69fe3 --- /dev/null +++ b/outputs/2023-12-11/11-44-36/.hydra/config.yaml @@ -0,0 +1,5 @@ +model_pretrain: /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +token_list: /Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +train_data_set_list: /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +output_dir: /Users/zhifu/Downloads/ckpt/funasr2/exp2 +device: cpu diff --git a/outputs/2023-12-11/11-44-36/.hydra/hydra.yaml b/outputs/2023-12-11/11-44-36/.hydra/hydra.yaml new file mode 100644 index 000000000..225a367d7 --- /dev/null +++ b/outputs/2023-12-11/11-44-36/.hydra/hydra.yaml @@ -0,0 +1,156 @@ +hydra: + run: + dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S} + sweep: + dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch + - +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt + - +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + - +output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2 + - +device=cpu + job: + name: train_cli + chdir: null + override_dirname: +device=cpu,+model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch,+output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2,+token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt,+train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + id: ??? + num: ??? + config_name: null + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.3.2 + version_base: '1.3' + cwd: /Users/zhifu/funasr_github + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: '' + schema: structured + provider: schema + output_dir: /Users/zhifu/funasr_github/outputs/2023-12-11/11-44-36 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/outputs/2023-12-11/11-44-36/.hydra/overrides.yaml b/outputs/2023-12-11/11-44-36/.hydra/overrides.yaml new file mode 100644 index 000000000..983d97f4f --- /dev/null +++ b/outputs/2023-12-11/11-44-36/.hydra/overrides.yaml @@ -0,0 +1,5 @@ +- +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +- +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +- +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +- +output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2 +- +device=cpu diff --git a/outputs/2023-12-11/11-44-36/train_cli.log b/outputs/2023-12-11/11-44-36/train_cli.log new file mode 100644 index 000000000..5ef50d6b9 --- /dev/null +++ b/outputs/2023-12-11/11-44-36/train_cli.log @@ -0,0 +1,2 @@ +[2023-12-11 11:44:48,432][root][INFO] - Loading pretrained params from /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.pb +[2023-12-11 11:44:49,667][root][WARNING] - distributed is not initialized, only single shard diff --git a/outputs/2023-12-11/11-48-01/.hydra/config.yaml b/outputs/2023-12-11/11-48-01/.hydra/config.yaml new file mode 100644 index 000000000..85ff69fe3 --- /dev/null +++ b/outputs/2023-12-11/11-48-01/.hydra/config.yaml @@ -0,0 +1,5 @@ +model_pretrain: /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +token_list: /Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +train_data_set_list: /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +output_dir: /Users/zhifu/Downloads/ckpt/funasr2/exp2 +device: cpu diff --git a/outputs/2023-12-11/11-48-01/.hydra/hydra.yaml b/outputs/2023-12-11/11-48-01/.hydra/hydra.yaml new file mode 100644 index 000000000..3579e9e9a --- /dev/null +++ b/outputs/2023-12-11/11-48-01/.hydra/hydra.yaml @@ -0,0 +1,156 @@ +hydra: + run: + dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S} + sweep: + dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch + - +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt + - +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + - +output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2 + - +device=cpu + job: + name: train_cli + chdir: null + override_dirname: +device=cpu,+model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch,+output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2,+token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt,+train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + id: ??? + num: ??? + config_name: null + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.3.2 + version_base: '1.3' + cwd: /Users/zhifu/funasr_github + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: '' + schema: structured + provider: schema + output_dir: /Users/zhifu/funasr_github/outputs/2023-12-11/11-48-01 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/outputs/2023-12-11/11-48-01/.hydra/overrides.yaml b/outputs/2023-12-11/11-48-01/.hydra/overrides.yaml new file mode 100644 index 000000000..983d97f4f --- /dev/null +++ b/outputs/2023-12-11/11-48-01/.hydra/overrides.yaml @@ -0,0 +1,5 @@ +- +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +- +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +- +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +- +output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2 +- +device=cpu diff --git a/outputs/2023-12-11/11-48-01/train_cli.log b/outputs/2023-12-11/11-48-01/train_cli.log new file mode 100644 index 000000000..3531939f8 --- /dev/null +++ b/outputs/2023-12-11/11-48-01/train_cli.log @@ -0,0 +1,3 @@ +[2023-12-11 11:48:05,427][root][INFO] - Loading pretrained params from /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.pb +[2023-12-11 11:48:07,007][root][WARNING] - distributed is not initialized, only single shard +[2023-12-11 11:48:07,026][root][WARNING] - distributed is not initialized, only single shard diff --git a/outputs/2023-12-11/13-06-39/.hydra/config.yaml b/outputs/2023-12-11/13-06-39/.hydra/config.yaml new file mode 100644 index 000000000..85ff69fe3 --- /dev/null +++ b/outputs/2023-12-11/13-06-39/.hydra/config.yaml @@ -0,0 +1,5 @@ +model_pretrain: /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +token_list: /Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +train_data_set_list: /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +output_dir: /Users/zhifu/Downloads/ckpt/funasr2/exp2 +device: cpu diff --git a/outputs/2023-12-11/13-06-39/.hydra/hydra.yaml b/outputs/2023-12-11/13-06-39/.hydra/hydra.yaml new file mode 100644 index 000000000..e92f2f885 --- /dev/null +++ b/outputs/2023-12-11/13-06-39/.hydra/hydra.yaml @@ -0,0 +1,156 @@ +hydra: + run: + dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S} + sweep: + dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch + - +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt + - +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + - +output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2 + - +device=cpu + job: + name: train_cli + chdir: null + override_dirname: +device=cpu,+model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch,+output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2,+token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt,+train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + id: ??? + num: ??? + config_name: null + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.3.2 + version_base: '1.3' + cwd: /Users/zhifu/funasr_github + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: '' + schema: structured + provider: schema + output_dir: /Users/zhifu/funasr_github/outputs/2023-12-11/13-06-39 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/outputs/2023-12-11/13-06-39/.hydra/overrides.yaml b/outputs/2023-12-11/13-06-39/.hydra/overrides.yaml new file mode 100644 index 000000000..983d97f4f --- /dev/null +++ b/outputs/2023-12-11/13-06-39/.hydra/overrides.yaml @@ -0,0 +1,5 @@ +- +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +- +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +- +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +- +output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2 +- +device=cpu diff --git a/outputs/2023-12-11/13-06-39/train_cli.log b/outputs/2023-12-11/13-06-39/train_cli.log new file mode 100644 index 000000000..e69de29bb diff --git a/outputs/2023-12-11/13-07-13/.hydra/config.yaml b/outputs/2023-12-11/13-07-13/.hydra/config.yaml new file mode 100644 index 000000000..85ff69fe3 --- /dev/null +++ b/outputs/2023-12-11/13-07-13/.hydra/config.yaml @@ -0,0 +1,5 @@ +model_pretrain: /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +token_list: /Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +train_data_set_list: /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +output_dir: /Users/zhifu/Downloads/ckpt/funasr2/exp2 +device: cpu diff --git a/outputs/2023-12-11/13-07-13/.hydra/hydra.yaml b/outputs/2023-12-11/13-07-13/.hydra/hydra.yaml new file mode 100644 index 000000000..f47436a6e --- /dev/null +++ b/outputs/2023-12-11/13-07-13/.hydra/hydra.yaml @@ -0,0 +1,156 @@ +hydra: + run: + dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S} + sweep: + dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch + - +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt + - +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + - +output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2 + - +device=cpu + job: + name: train_cli + chdir: null + override_dirname: +device=cpu,+model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch,+output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2,+token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt,+train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + id: ??? + num: ??? + config_name: null + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.3.2 + version_base: '1.3' + cwd: /Users/zhifu/funasr_github + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: '' + schema: structured + provider: schema + output_dir: /Users/zhifu/funasr_github/outputs/2023-12-11/13-07-13 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/outputs/2023-12-11/13-07-13/.hydra/overrides.yaml b/outputs/2023-12-11/13-07-13/.hydra/overrides.yaml new file mode 100644 index 000000000..983d97f4f --- /dev/null +++ b/outputs/2023-12-11/13-07-13/.hydra/overrides.yaml @@ -0,0 +1,5 @@ +- +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +- +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +- +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +- +output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2 +- +device=cpu diff --git a/outputs/2023-12-11/13-07-13/train_cli.log b/outputs/2023-12-11/13-07-13/train_cli.log new file mode 100644 index 000000000..74bb187fc --- /dev/null +++ b/outputs/2023-12-11/13-07-13/train_cli.log @@ -0,0 +1,3 @@ +[2023-12-11 13:07:30,599][root][INFO] - Loading pretrained params from /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.pb +[2023-12-11 13:07:31,757][root][WARNING] - distributed is not initialized, only single shard +[2023-12-11 13:07:31,859][root][WARNING] - distributed is not initialized, only single shard diff --git a/outputs/2023-12-11/13-12-46/.hydra/config.yaml b/outputs/2023-12-11/13-12-46/.hydra/config.yaml new file mode 100644 index 000000000..85ff69fe3 --- /dev/null +++ b/outputs/2023-12-11/13-12-46/.hydra/config.yaml @@ -0,0 +1,5 @@ +model_pretrain: /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +token_list: /Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +train_data_set_list: /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +output_dir: /Users/zhifu/Downloads/ckpt/funasr2/exp2 +device: cpu diff --git a/outputs/2023-12-11/13-12-46/.hydra/hydra.yaml b/outputs/2023-12-11/13-12-46/.hydra/hydra.yaml new file mode 100644 index 000000000..c0a361eb6 --- /dev/null +++ b/outputs/2023-12-11/13-12-46/.hydra/hydra.yaml @@ -0,0 +1,156 @@ +hydra: + run: + dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S} + sweep: + dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch + - +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt + - +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + - +output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2 + - +device=cpu + job: + name: train_cli + chdir: null + override_dirname: +device=cpu,+model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch,+output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2,+token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt,+train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + id: ??? + num: ??? + config_name: null + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.3.2 + version_base: '1.3' + cwd: /Users/zhifu/funasr_github + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: '' + schema: structured + provider: schema + output_dir: /Users/zhifu/funasr_github/outputs/2023-12-11/13-12-46 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/outputs/2023-12-11/13-12-46/.hydra/overrides.yaml b/outputs/2023-12-11/13-12-46/.hydra/overrides.yaml new file mode 100644 index 000000000..983d97f4f --- /dev/null +++ b/outputs/2023-12-11/13-12-46/.hydra/overrides.yaml @@ -0,0 +1,5 @@ +- +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +- +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +- +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +- +output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2 +- +device=cpu diff --git a/outputs/2023-12-11/13-12-46/train_cli.log b/outputs/2023-12-11/13-12-46/train_cli.log new file mode 100644 index 000000000..1aed15c96 --- /dev/null +++ b/outputs/2023-12-11/13-12-46/train_cli.log @@ -0,0 +1,5 @@ +[2023-12-11 13:12:51,157][root][INFO] - init_param is not None: ('/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.pb',) +[2023-12-11 13:12:51,157][root][INFO] - Loading pretrained params from /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.pb +[2023-12-11 13:12:52,231][root][WARNING] - distributed is not initialized, only single shard +[2023-12-11 13:12:52,266][root][INFO] - config.yaml is saved to: /Users/zhifu/Downloads/ckpt/funasr2/exp2/config.yaml +[2023-12-11 13:12:52,266][root][WARNING] - distributed is not initialized, only single shard diff --git a/outputs/2023-12-11/13-16-01/.hydra/config.yaml b/outputs/2023-12-11/13-16-01/.hydra/config.yaml new file mode 100644 index 000000000..85ff69fe3 --- /dev/null +++ b/outputs/2023-12-11/13-16-01/.hydra/config.yaml @@ -0,0 +1,5 @@ +model_pretrain: /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +token_list: /Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +train_data_set_list: /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +output_dir: /Users/zhifu/Downloads/ckpt/funasr2/exp2 +device: cpu diff --git a/outputs/2023-12-11/13-16-01/.hydra/hydra.yaml b/outputs/2023-12-11/13-16-01/.hydra/hydra.yaml new file mode 100644 index 000000000..dc3278422 --- /dev/null +++ b/outputs/2023-12-11/13-16-01/.hydra/hydra.yaml @@ -0,0 +1,156 @@ +hydra: + run: + dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S} + sweep: + dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch + - +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt + - +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + - +output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2 + - +device=cpu + job: + name: train_cli + chdir: null + override_dirname: +device=cpu,+model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch,+output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2,+token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt,+train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + id: ??? + num: ??? + config_name: null + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.3.2 + version_base: '1.3' + cwd: /Users/zhifu/funasr_github + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: '' + schema: structured + provider: schema + output_dir: /Users/zhifu/funasr_github/outputs/2023-12-11/13-16-01 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/outputs/2023-12-11/13-16-01/.hydra/overrides.yaml b/outputs/2023-12-11/13-16-01/.hydra/overrides.yaml new file mode 100644 index 000000000..983d97f4f --- /dev/null +++ b/outputs/2023-12-11/13-16-01/.hydra/overrides.yaml @@ -0,0 +1,5 @@ +- +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +- +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +- +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +- +output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2 +- +device=cpu diff --git a/outputs/2023-12-11/13-16-01/train_cli.log b/outputs/2023-12-11/13-16-01/train_cli.log new file mode 100644 index 000000000..66787f99a --- /dev/null +++ b/outputs/2023-12-11/13-16-01/train_cli.log @@ -0,0 +1,6 @@ +[2023-12-11 13:16:27,835][root][INFO] - init_param is not None: ('/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.pb',) +[2023-12-11 13:16:27,835][root][INFO] - Loading pretrained params from /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.pb +[2023-12-11 13:16:28,828][root][WARNING] - distributed is not initialized, only single shard +[2023-12-11 13:16:28,828][root][INFO] - in rank: 0, num of samplers: 640, total_num of samplers across ranks: 640 +[2023-12-11 13:16:28,835][root][INFO] - config.yaml is saved to: /Users/zhifu/Downloads/ckpt/funasr2/exp2/config.yaml +[2023-12-11 13:16:28,835][root][WARNING] - distributed is not initialized, only single shard diff --git a/outputs/2023-12-11/13-19-05/.hydra/config.yaml b/outputs/2023-12-11/13-19-05/.hydra/config.yaml new file mode 100644 index 000000000..85ff69fe3 --- /dev/null +++ b/outputs/2023-12-11/13-19-05/.hydra/config.yaml @@ -0,0 +1,5 @@ +model_pretrain: /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +token_list: /Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +train_data_set_list: /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +output_dir: /Users/zhifu/Downloads/ckpt/funasr2/exp2 +device: cpu diff --git a/outputs/2023-12-11/13-19-05/.hydra/hydra.yaml b/outputs/2023-12-11/13-19-05/.hydra/hydra.yaml new file mode 100644 index 000000000..d89b6c11b --- /dev/null +++ b/outputs/2023-12-11/13-19-05/.hydra/hydra.yaml @@ -0,0 +1,156 @@ +hydra: + run: + dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S} + sweep: + dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch + - +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt + - +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + - +output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2 + - +device=cpu + job: + name: train_cli + chdir: null + override_dirname: +device=cpu,+model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch,+output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2,+token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt,+train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + id: ??? + num: ??? + config_name: null + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.3.2 + version_base: '1.3' + cwd: /Users/zhifu/funasr_github + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: '' + schema: structured + provider: schema + output_dir: /Users/zhifu/funasr_github/outputs/2023-12-11/13-19-05 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/outputs/2023-12-11/13-19-05/.hydra/overrides.yaml b/outputs/2023-12-11/13-19-05/.hydra/overrides.yaml new file mode 100644 index 000000000..983d97f4f --- /dev/null +++ b/outputs/2023-12-11/13-19-05/.hydra/overrides.yaml @@ -0,0 +1,5 @@ +- +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +- +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +- +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +- +output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2 +- +device=cpu diff --git a/outputs/2023-12-11/13-19-05/train_cli.log b/outputs/2023-12-11/13-19-05/train_cli.log new file mode 100644 index 000000000..1832e8ed1 --- /dev/null +++ b/outputs/2023-12-11/13-19-05/train_cli.log @@ -0,0 +1,6 @@ +[2023-12-11 13:19:09,868][root][INFO] - init_param is not None: ('/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.pb',) +[2023-12-11 13:19:09,868][root][INFO] - Loading pretrained params from /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.pb +[2023-12-11 13:19:11,006][root][WARNING] - distributed is not initialized, only single shard +[2023-12-11 13:19:11,006][root][INFO] - in rank: 0, num of samplers: 640, total_num of samplers across ranks: 640 +[2023-12-11 13:19:11,014][root][INFO] - config.yaml is saved to: /Users/zhifu/Downloads/ckpt/funasr2/exp2/config.yaml +[2023-12-11 13:19:11,014][root][WARNING] - distributed is not initialized, only single shard diff --git a/outputs/2023-12-11/13-24-15/.hydra/config.yaml b/outputs/2023-12-11/13-24-15/.hydra/config.yaml new file mode 100644 index 000000000..85ff69fe3 --- /dev/null +++ b/outputs/2023-12-11/13-24-15/.hydra/config.yaml @@ -0,0 +1,5 @@ +model_pretrain: /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +token_list: /Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +train_data_set_list: /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +output_dir: /Users/zhifu/Downloads/ckpt/funasr2/exp2 +device: cpu diff --git a/outputs/2023-12-11/13-24-15/.hydra/hydra.yaml b/outputs/2023-12-11/13-24-15/.hydra/hydra.yaml new file mode 100644 index 000000000..37decbbc4 --- /dev/null +++ b/outputs/2023-12-11/13-24-15/.hydra/hydra.yaml @@ -0,0 +1,156 @@ +hydra: + run: + dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S} + sweep: + dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch + - +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt + - +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + - +output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2 + - +device=cpu + job: + name: train_cli + chdir: null + override_dirname: +device=cpu,+model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch,+output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2,+token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt,+train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + id: ??? + num: ??? + config_name: null + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.3.2 + version_base: '1.3' + cwd: /Users/zhifu/funasr_github + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: '' + schema: structured + provider: schema + output_dir: /Users/zhifu/funasr_github/outputs/2023-12-11/13-24-15 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/outputs/2023-12-11/13-24-15/.hydra/overrides.yaml b/outputs/2023-12-11/13-24-15/.hydra/overrides.yaml new file mode 100644 index 000000000..983d97f4f --- /dev/null +++ b/outputs/2023-12-11/13-24-15/.hydra/overrides.yaml @@ -0,0 +1,5 @@ +- +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +- +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +- +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +- +output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2 +- +device=cpu diff --git a/outputs/2023-12-11/13-24-15/train_cli.log b/outputs/2023-12-11/13-24-15/train_cli.log new file mode 100644 index 000000000..06122f2be --- /dev/null +++ b/outputs/2023-12-11/13-24-15/train_cli.log @@ -0,0 +1,6 @@ +[2023-12-11 13:24:21,397][root][INFO] - init_param is not None: ('/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.pb',) +[2023-12-11 13:24:21,397][root][INFO] - Loading pretrained params from /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.pb +[2023-12-11 13:24:21,980][root][WARNING] - distributed is not initialized, only single shard +[2023-12-11 13:24:21,980][root][INFO] - in rank: 0, num of samplers: 640, total_num of samplers across ranks: 640 +[2023-12-11 13:24:21,987][root][INFO] - config.yaml is saved to: /Users/zhifu/Downloads/ckpt/funasr2/exp2/config.yaml +[2023-12-11 13:24:21,987][root][WARNING] - distributed is not initialized, only single shard diff --git a/outputs/2023-12-11/13-37-51/.hydra/config.yaml b/outputs/2023-12-11/13-37-51/.hydra/config.yaml new file mode 100644 index 000000000..85ff69fe3 --- /dev/null +++ b/outputs/2023-12-11/13-37-51/.hydra/config.yaml @@ -0,0 +1,5 @@ +model_pretrain: /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +token_list: /Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +train_data_set_list: /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +output_dir: /Users/zhifu/Downloads/ckpt/funasr2/exp2 +device: cpu diff --git a/outputs/2023-12-11/13-37-51/.hydra/hydra.yaml b/outputs/2023-12-11/13-37-51/.hydra/hydra.yaml new file mode 100644 index 000000000..7a168d7d1 --- /dev/null +++ b/outputs/2023-12-11/13-37-51/.hydra/hydra.yaml @@ -0,0 +1,156 @@ +hydra: + run: + dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S} + sweep: + dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch + - +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt + - +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + - +output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2 + - +device=cpu + job: + name: train_cli + chdir: null + override_dirname: +device=cpu,+model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch,+output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2,+token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt,+train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + id: ??? + num: ??? + config_name: null + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.3.2 + version_base: '1.3' + cwd: /Users/zhifu/funasr_github + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: '' + schema: structured + provider: schema + output_dir: /Users/zhifu/funasr_github/outputs/2023-12-11/13-37-51 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/outputs/2023-12-11/13-37-51/.hydra/overrides.yaml b/outputs/2023-12-11/13-37-51/.hydra/overrides.yaml new file mode 100644 index 000000000..983d97f4f --- /dev/null +++ b/outputs/2023-12-11/13-37-51/.hydra/overrides.yaml @@ -0,0 +1,5 @@ +- +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +- +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +- +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +- +output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2 +- +device=cpu diff --git a/outputs/2023-12-11/13-37-51/train_cli.log b/outputs/2023-12-11/13-37-51/train_cli.log new file mode 100644 index 000000000..724cc0df3 --- /dev/null +++ b/outputs/2023-12-11/13-37-51/train_cli.log @@ -0,0 +1,6 @@ +[2023-12-11 13:38:00,018][root][INFO] - init_param is not None: ('/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.pb',) +[2023-12-11 13:38:00,019][root][INFO] - Loading pretrained params from /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.pb +[2023-12-11 13:38:01,162][root][WARNING] - distributed is not initialized, only single shard +[2023-12-11 13:38:01,162][root][INFO] - in rank: 0, num of samplers: 640, total_num of samplers across ranks: 640 +[2023-12-11 13:38:01,248][root][INFO] - config.yaml is saved to: /Users/zhifu/Downloads/ckpt/funasr2/exp2/config.yaml +[2023-12-11 13:38:01,249][root][WARNING] - distributed is not initialized, only single shard diff --git a/outputs/2023-12-11/13-39-37/.hydra/config.yaml b/outputs/2023-12-11/13-39-37/.hydra/config.yaml new file mode 100644 index 000000000..85ff69fe3 --- /dev/null +++ b/outputs/2023-12-11/13-39-37/.hydra/config.yaml @@ -0,0 +1,5 @@ +model_pretrain: /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +token_list: /Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +train_data_set_list: /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +output_dir: /Users/zhifu/Downloads/ckpt/funasr2/exp2 +device: cpu diff --git a/outputs/2023-12-11/13-39-37/.hydra/hydra.yaml b/outputs/2023-12-11/13-39-37/.hydra/hydra.yaml new file mode 100644 index 000000000..85aae4351 --- /dev/null +++ b/outputs/2023-12-11/13-39-37/.hydra/hydra.yaml @@ -0,0 +1,156 @@ +hydra: + run: + dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S} + sweep: + dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S} + subdir: ${hydra.job.num} + launcher: + _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher + sweeper: + _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper + max_batch_size: null + params: null + help: + app_name: ${hydra.job.name} + header: '${hydra.help.app_name} is powered by Hydra. + + ' + footer: 'Powered by Hydra (https://hydra.cc) + + Use --hydra-help to view Hydra specific help + + ' + template: '${hydra.help.header} + + == Configuration groups == + + Compose your configuration from those groups (group=option) + + + $APP_CONFIG_GROUPS + + + == Config == + + Override anything in the config (foo.bar=value) + + + $CONFIG + + + ${hydra.help.footer} + + ' + hydra_help: + template: 'Hydra (${hydra.runtime.version}) + + See https://hydra.cc for more info. + + + == Flags == + + $FLAGS_HELP + + + == Configuration groups == + + Compose your configuration from those groups (For example, append hydra/job_logging=disabled + to command line) + + + $HYDRA_CONFIG_GROUPS + + + Use ''--cfg hydra'' to Show the Hydra config. + + ' + hydra_help: ??? + hydra_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][HYDRA] %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + root: + level: INFO + handlers: + - console + loggers: + logging_example: + level: DEBUG + disable_existing_loggers: false + job_logging: + version: 1 + formatters: + simple: + format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s' + handlers: + console: + class: logging.StreamHandler + formatter: simple + stream: ext://sys.stdout + file: + class: logging.FileHandler + formatter: simple + filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log + root: + level: INFO + handlers: + - console + - file + disable_existing_loggers: false + env: {} + mode: RUN + searchpath: [] + callbacks: {} + output_subdir: .hydra + overrides: + hydra: + - hydra.mode=RUN + task: + - +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch + - +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt + - +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + - +output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2 + - +device=cpu + job: + name: train_cli + chdir: null + override_dirname: +device=cpu,+model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch,+output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2,+token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt,+train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl + id: ??? + num: ??? + config_name: null + env_set: {} + env_copy: [] + config: + override_dirname: + kv_sep: '=' + item_sep: ',' + exclude_keys: [] + runtime: + version: 1.3.2 + version_base: '1.3' + cwd: /Users/zhifu/funasr_github + config_sources: + - path: hydra.conf + schema: pkg + provider: hydra + - path: '' + schema: structured + provider: schema + output_dir: /Users/zhifu/funasr_github/outputs/2023-12-11/13-39-37 + choices: + hydra/env: default + hydra/callbacks: null + hydra/job_logging: default + hydra/hydra_logging: default + hydra/hydra_help: default + hydra/help: default + hydra/sweeper: basic + hydra/launcher: basic + hydra/output: default + verbose: false diff --git a/outputs/2023-12-11/13-39-37/.hydra/overrides.yaml b/outputs/2023-12-11/13-39-37/.hydra/overrides.yaml new file mode 100644 index 000000000..983d97f4f --- /dev/null +++ b/outputs/2023-12-11/13-39-37/.hydra/overrides.yaml @@ -0,0 +1,5 @@ +- +model_pretrain=/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +- +token_list=/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt +- +train_data_set_list=/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl +- +output_dir=/Users/zhifu/Downloads/ckpt/funasr2/exp2 +- +device=cpu diff --git a/outputs/2023-12-11/13-39-37/train_cli.log b/outputs/2023-12-11/13-39-37/train_cli.log new file mode 100644 index 000000000..42386288a --- /dev/null +++ b/outputs/2023-12-11/13-39-37/train_cli.log @@ -0,0 +1,6 @@ +[2023-12-11 13:39:40,353][root][INFO] - init_param is not None: ('/Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.pb',) +[2023-12-11 13:39:40,353][root][INFO] - Loading pretrained params from /Users/zhifu/modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.pb +[2023-12-11 13:39:41,780][root][WARNING] - distributed is not initialized, only single shard +[2023-12-11 13:39:41,780][root][INFO] - in rank: 0, num of samplers: 640, total_num of samplers across ranks: 640 +[2023-12-11 13:39:41,861][root][INFO] - config.yaml is saved to: /Users/zhifu/Downloads/ckpt/funasr2/exp2/config.yaml +[2023-12-11 13:39:41,862][root][WARNING] - distributed is not initialized, only single shard