python whisperx 报错 in load_align_model raise ValueError(f'The chosen align_model "{model_name}" - 查问我看

转 Python 学习整理2

|-转 python whisperx 报错 in load_align_model raise ValueError(f'The chosen align_model "{model_name}"

PHPer 2025-08-23 1 0 0

raise ValueError(f'The chosen align_model "{model_name}" could not be found in huggingface (https://huggingface.co/models) or torchaudio (https://pytorch.org/audio/stable/pipelines.html#id14)')
ValueError: The chosen align_model "jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn" could not be found in huggingface (https://huggingface.co/models) or torchaudio (https://pytorch.org/audio/stable/pipelines.html#id14)

requests.exceptions.ConnectionError: (MaxRetryError("HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /api/models/jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn/tree/main/additional_chat_templates?recursive=False&expand=False (Caused by NewConnectionError(': Failed to establish a new connection: [WinError 10060] 由于连接方在一段时间后没有正确答复或连接的主机没有反应，连接尝试失败。'))"), '(Request ID: ee57b154-cd73-4a1a-911a-a89c496c8b20)')

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "D:\python\fastapi-speaker-extractor\app\api\endpoints.py", line 25, in extract_speaker
    result = await process_audio(audio_file.file, config_value, whisper_model, device)
  File "D:\python\fastapi-speaker-extractor\app\services\audio_processor.py", line 25, in process_audio
    model_a, metadata = whisperx.load_align_model(language_code="zh", device=device)
  File "G:\ProgramData\miniconda3\envs\speaker-extractor\lib\site-packages\whisperx\__init__.py", line 11, in load_align_model
    return alignment.load_align_model(*args, **kwargs)
  File "G:\ProgramData\miniconda3\envs\speaker-extractor\lib\site-packages\whisperx\alignment.py", line 102, in load_align_model
    raise ValueError(f'The chosen align_model "{model_name}" could not be found in huggingface (https://huggingface.co/models) or torchaudio (https://pytorch.org/audio/stable/pipelines.html#id14)')
ValueError: The chosen align_model "jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn" could not be found in huggingface (https://huggingface.co/models) or torchaudio (https://pytorch.org/audio/stable/pipelines.html#id14)
INFO:     127.0.0.1:1141 - "POST /api/speaker/extract/?config_value=default HTTP/1.1" 500 Internal Server Error

由于网络原因，会访问hugging face官网，但是网络无法访问，所有报错。...