#6804 语音识别阶段出错[阿里FunASR(本地内置)] NoneTraceback (most recent call last):

125.67.**8 Posted at: 10 hours ago

语音识别阶段出错[阿里FunASR(本地内置)] None
Traceback (most recent call last):

File "videotrans\task\job.py", line 35, in run

File "videotrans\task\job.py", line 100, in process_task

File "videotrans\task\speech2text.py", line 97, in recogn

File "videotrans\recognition\__init__.py", line 206, in run

File "videotrans\recognition\_base.py", line 92, in run

File "videotrans\recognition\_funasr.py", line 48, in _exec

File "videotrans\recognition\_base.py", line 208, in cut_audio

File "videotrans\recognition\_base.py", line 189, in _vad_split

File "videotrans\configure\base.py", line 272, in _new_process

videotrans.configure.excepts.VideoTransError: None
cfg=TaskCfgSTT(uuid='39b169e38f', name='D:/BaiduNetdiskDownload/Youtube/排列好了的/059.Divisimate 1.3 is out and its a free update.mp4', dirname='D:/BaiduNetdiskDownload/Youtube/排列好了的', noextname='059.Divisimate 1.3 is out and its a free update', basename='059.Divisimate 1.3 is out and its a free update.mp4', ext='mp4', target_dir='D:/BaiduNetdiskDownload/pyVideoTrans/win-pyvideotrans-v4.07/output/recogn', cache_folder='D:/BaiduNetdiskDownload/pyVideoTrans/win-pyvideotrans-v4.07/tmp/10780/39b169e38f', is_cuda=True, source_language=None, source_language_code=None, source_sub=None, source_wav=None, source_wav_output=None, target_language=None, target_language_code=None, target_sub='D:/BaiduNetdiskDownload/pyVideoTrans/win-pyvideotrans-v4.07/output/recogn/059.Divisimate 1.3 is out and its a free update.srt', target_wav=None, target_wav_output=None, detect_language='en', recogn_type=3, model_name='Fun-ASR-Nano-2512', shibie_audio='D:/BaiduNetdiskDownload/pyVideoTrans/win-pyvideotrans-v4.07/tmp/10780/39b169e38f/059.Divisimate 1.3 is out and its a free update-1787323300.2437346.wav', remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=0)


=
system:Windows-10-10.0.26100-SP0
version:v4.07
frozen:True
language:zh
root_dir:D:/BaiduNetdiskDownload/pyVideoTrans/win-pyvideotrans-v4.07

1 Replies

#1 DeepSeek reply at 10 hours ago

错误发生在 VAD 预分割阶段,核心原因通常是 FunASR 相关的 VAD 模型文件缺失、未下载完整或缓存损坏。

请按以下步骤排查:

  1. 检查模型完整性
    打开软件目录下的 models/onnx/ 文件夹,确认是否存在以下文件(缺失会导致 VAD 分割直接中断):

    • seg_model.onnx(VAD 分割模型)
    • 3dspeaker_speech_eres2net_large_sv_zh-cn_3dspeaker_16k.onnx
    • nemo_en_titanet_small.onnx
  2. 手动下载缺失模型
    若缺少文件,请从以下地址下载全部 .onnx 文件并放入 软件目录/models/onnx/
    https://modelscope.cn/models/himyworld/videotrans/tree/master/onnx
  3. 验证 FunASR 主模型
    检查 软件目录/models/ 下是否存在 FunASR 模型目录。首次使用需在线下载,若自动下载失败则需手动放置。
  4. 临时代替方案
    若仍需紧急处理,可先将语音识别渠道切换为 faster-whisper(内置),该渠道不依赖 onnx VAD 模型,可先行完成任务。
  5. 补充信息
    若以上操作后仍报错,请提供 logs/ 目录下最新日志文件的末尾约 30 行内容,以便进一步定位。
Thinking...
Post Your Reply
Open source and free maintenance is not easy. If this project is helpful to you, please consider making a small donation to help the project continue to maintain and update.

Dondate via ko-fi.com

Related resource