add

examples/industrial_data_pretraining/llm_asr/conf/whisper_qwen_linear2.yaml

@@ -1,81 +0,0 @@
-# This is an example that demonstrates how to configure a model file.
-# You can modify the configuration according to your own requirements.
-
-# to print the register_table:
-# from funasr.register import tables
-# tables.print()
-
-# network architecture
-model: LLMASR2
-model_conf:
-    lsm_weight: 0.1     # label smoothing option
-    length_normalized_loss: true
-
-# encoder
-audio_encoder: "/nfs/zhifu.gzf/init_model/SenseVoiceModelscope"
-audio_encoder_conf:
-    hub: ms
-    freeze: true
-
-llm: Qwen1.5-7b-chat
-llm_conf:
-  hub: hf
-  freeze: true
-  init_param_path: "/nfs/zhifu.gzf/init_model/qwen/Qwen1___5-7B-Chat_raw"
-
-audio_adaptor: Transformer
-audio_adaptor_conf:
-  downsample_rate: 2
-  llm_dim: 4096
-  encoder_dim: 1280
-  n_layer: 0
-
-# frontend related
-frontend: WhisperFrontend
-frontend_conf:
-    fs: 16000
-    whisper_model: large-v3
-    do_pad_trim: false
-    permute: false # true: [bs, frames, dims]; false: [bs, dims, frames]
-    filters_path: "/nfs/zhifu.gzf/init_model/SenseVoiceModelscope/assets/mel_filters.npz"
-
-
-
-train_conf:
-  accum_grad: 1
-  grad_clip: 5
-  max_epoch: 15
-  keep_nbest_models: 10
-  log_interval: 10
-
-optim: adamw
-optim_conf:
-   lr: 0.0001
-   weight_decay: 0.000000
-
-scheduler: warmuplr
-scheduler_conf:
-   warmup_steps: 1500
-
-dataset: OpenAIDataset
-dataset_conf:
-  index_ds: OpenAIIndexDSJsonl
-  batch_sampler: BatchSampler
-  batch_type: token
-  batch_size: 900
-  max_token_length: 1024
-  shuffle: true
-  sort_size: 1024
-  batch_size_scale_ratio_max: 2
-  num_workers: 4
-  audio_adaptor_downsample_rate: ${audio_adaptor_conf.downsample_rate}
-  audio_encoder_downsample_rate: 4
-  data_split_num: 512
-  batch_size_sample_max: 15
-  retry: 20
-
-
-tokenizer: HuggingfaceTokenizer
-tokenizer_conf:
-  init_param_path: "/nfs/zhifu.gzf/init_model/qwen/Qwen1___5-7B-Chat_raw"
-

examples/industrial_data_pretraining/llm_asr/conf/whisper_qwen_transformer.yaml

@@ -1,81 +0,0 @@
-# This is an example that demonstrates how to configure a model file.
-# You can modify the configuration according to your own requirements.
-
-# to print the register_table:
-# from funasr.register import tables
-# tables.print()
-
-# network architecture
-model: LLMASR2
-model_conf:
-    lsm_weight: 0.1     # label smoothing option
-    length_normalized_loss: true
-
-# encoder
-audio_encoder: "/nfs/zhifu.gzf/init_model/SenseVoiceModelscope"
-audio_encoder_conf:
-    hub: ms
-    freeze: true
-
-llm: Qwen1.5-7b-chat
-llm_conf:
-  hub: hf
-  freeze: true
-  init_param_path: "/nfs/zhifu.gzf/init_model/qwen/Qwen1___5-7B-Chat_raw"
-
-audio_adaptor: Transformer
-audio_adaptor_conf:
-  downsample_rate: 2
-  llm_dim: 4096
-  encoder_dim: 1280
-  n_layer: 2
-
-# frontend related
-frontend: WhisperFrontend
-frontend_conf:
-    fs: 16000
-    whisper_model: large-v3
-    do_pad_trim: false
-    permute: false # true: [bs, frames, dims]; false: [bs, dims, frames]
-    filters_path: "/nfs/zhifu.gzf/init_model/SenseVoiceModelscope/assets/mel_filters.npz"
-
-
-
-train_conf:
-  accum_grad: 1
-  grad_clip: 5
-  max_epoch: 15
-  keep_nbest_models: 10
-  log_interval: 10
-
-optim: adamw
-optim_conf:
-   lr: 0.0001
-   weight_decay: 0.000000
-
-scheduler: warmuplr
-scheduler_conf:
-   warmup_steps: 1500
-
-dataset: OpenAIDataset
-dataset_conf:
-  index_ds: OpenAIIndexDSJsonl
-  batch_sampler: BatchSampler
-  batch_type: token
-  batch_size: 900
-  max_token_length: 1024
-  shuffle: true
-  sort_size: 1024
-  batch_size_scale_ratio_max: 2
-  num_workers: 4
-  audio_adaptor_downsample_rate: ${audio_adaptor_conf.downsample_rate}
-  audio_encoder_downsample_rate: 2
-  data_split_num: 512
-  batch_size_sample_max: 15
-  retry: 20
-
-
-tokenizer: HuggingfaceTokenizer
-tokenizer_conf:
-  init_param_path: "/nfs/zhifu.gzf/init_model/qwen/Qwen1___5-7B-Chat_raw"
-