speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

train finetune

Browse Source
This commit is contained in:
游雁 2024-02-20 18:38:51 +08:00
parent 2e8dc0933f
commit 96e4ff1870
6 changed files with 11 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
examples/aishell/branchformer/conf/branchformer_12e_6d_2048_256.yaml
View File

@ -108,7 +108,6 @@ dataset_conf:
tokenizer: CharTokenizer
tokenizer_conf:
unk_symbol: <unk>
split_with_space: true
ctc_conf:

2
examples/aishell/conformer/conf/conformer_12e_6d_2048_256.yaml
View File

@ -108,8 +108,6 @@ dataset_conf:
tokenizer: CharTokenizer
tokenizer_conf:
unk_symbol: <unk>
split_with_space: true
ctc_conf:
dropout_rate: 0.0

1
examples/aishell/e_branchformer/conf/e_branchformer_12e_6d_2048_256.yaml
View File

@ -108,7 +108,6 @@ dataset_conf:
tokenizer: CharTokenizer
tokenizer_conf:
unk_symbol: <unk>
split_with_space: true
ctc_conf:

2
examples/aishell/paraformer/conf/paraformer_conformer_12e_6d_2048_256.yaml
View File

@ -107,8 +107,6 @@ dataset_conf:
tokenizer: CharTokenizer
tokenizer_conf:
unk_symbol: <unk>
split_with_space: false
ctc_conf:
dropout_rate: 0.0

2
examples/aishell/transformer/conf/transformer_12e_6d_2048_256.yaml
View File

@ -102,8 +102,6 @@ dataset_conf:
tokenizer: CharTokenizer
tokenizer_conf:
unk_symbol: <unk>
split_with_space: true
ctc_conf:
dropout_rate: 0.0

24
funasr/download/download_from_hub.py
View File

@ -21,10 +21,17 @@ def download_from_ms(**kwargs):
model_or_path = get_or_download_model_dir(model_or_path, model_revision, is_training=kwargs.get("is_training"), check_latest=kwargs.get("kwargs", True))
kwargs["model_path"] = model_or_path
config = os.path.join(model_or_path, "config.yaml")
if os.path.exists(config) and os.path.exists(os.path.join(model_or_path, "model.pb")):
config = OmegaConf.load(config)
if os.path.exists(os.path.join(model_or_path, "configuration.json")):
with open(os.path.join(model_or_path, "configuration.json"), 'r', encoding='utf-8') as f:
conf_json = json.load(f)
cfg = {}
add_file_root_path(model_or_path, conf_json["file_path_metas"], cfg)
cfg.update(kwargs)
config = OmegaConf.load(cfg["config"])
kwargs = OmegaConf.merge(config, cfg)
kwargs["model"] = config["model"]
elif os.path.exists(os.path.join(model_or_path, "config.yaml")) and os.path.exists(os.path.join(model_or_path, "model.pt")):
config = OmegaConf.load(os.path.join(model_or_path, "config.yaml"))
kwargs = OmegaConf.merge(config, kwargs)
init_param = os.path.join(model_or_path, "model.pb")
kwargs["init_param"] = init_param
@ -41,15 +48,6 @@ def download_from_ms(**kwargs):
kwargs["frontend_conf"]["cmvn_file"] = os.path.join(model_or_path, "am.mvn")
if os.path.exists(os.path.join(model_or_path, "jieba_usr_dict")):
kwargs["jieba_usr_dict"] = os.path.join(model_or_path, "jieba_usr_dict")
elif os.path.exists(os.path.join(model_or_path, "configuration.json")):
with open(os.path.join(model_or_path, "configuration.json"), 'r', encoding='utf-8') as f:
conf_json = json.load(f)
cfg = {}
add_file_root_path(model_or_path, conf_json["file_path_metas"], cfg)
cfg.update(kwargs)
config = OmegaConf.load(cfg["config"])
kwargs = OmegaConf.merge(config, cfg)
kwargs["model"] = config["model"]
return OmegaConf.to_container(kwargs, resolve=True)
def add_file_root_path(model_or_path: str, file_path_metas: dict, cfg = {}):