游雁
2024-02-20 96e4ff1870656b6b9d10de5f1a994959b286b909
train finetune
6个文件已修改
32 ■■■■■ 已修改文件
examples/aishell/branchformer/conf/branchformer_12e_6d_2048_256.yaml 1 ●●●● 补丁 | 查看 | 原始文档 | blame | 历史
examples/aishell/conformer/conf/conformer_12e_6d_2048_256.yaml 2 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
examples/aishell/e_branchformer/conf/e_branchformer_12e_6d_2048_256.yaml 1 ●●●● 补丁 | 查看 | 原始文档 | blame | 历史
examples/aishell/paraformer/conf/paraformer_conformer_12e_6d_2048_256.yaml 2 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
examples/aishell/transformer/conf/transformer_12e_6d_2048_256.yaml 2 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/download/download_from_hub.py 24 ●●●● 补丁 | 查看 | 原始文档 | blame | 历史
examples/aishell/branchformer/conf/branchformer_12e_6d_2048_256.yaml
@@ -108,7 +108,6 @@
tokenizer: CharTokenizer
tokenizer_conf:
  unk_symbol: <unk>
  split_with_space: true
ctc_conf:
examples/aishell/conformer/conf/conformer_12e_6d_2048_256.yaml
@@ -108,8 +108,6 @@
tokenizer: CharTokenizer
tokenizer_conf:
  unk_symbol: <unk>
  split_with_space: true
ctc_conf:
    dropout_rate: 0.0
examples/aishell/e_branchformer/conf/e_branchformer_12e_6d_2048_256.yaml
@@ -108,7 +108,6 @@
tokenizer: CharTokenizer
tokenizer_conf:
  unk_symbol: <unk>
  split_with_space: true
ctc_conf:
examples/aishell/paraformer/conf/paraformer_conformer_12e_6d_2048_256.yaml
@@ -107,8 +107,6 @@
tokenizer: CharTokenizer
tokenizer_conf:
  unk_symbol: <unk>
  split_with_space: false
ctc_conf:
    dropout_rate: 0.0
examples/aishell/transformer/conf/transformer_12e_6d_2048_256.yaml
@@ -102,8 +102,6 @@
tokenizer: CharTokenizer
tokenizer_conf:
  unk_symbol: <unk>
  split_with_space: true
ctc_conf:
    dropout_rate: 0.0
funasr/download/download_from_hub.py
@@ -21,10 +21,17 @@
        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 @@
            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 = {}):