#3889 TaskCfgSTT(is_cuda=True, uuid='7b04c8cb75', cache_folder='D:/hai/AI/win-pyvideotrans/tmp/19868/7b04c8cb75', target_dir='

45.62* Posted at: 1 day ago 👁18

语音识别阶段出错 [阿里FunASR(本地)] Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 898, in funasr_mlt
File "funasr\auto\auto_model.py", line 135, in init

model, kwargs = self.build_model(**kwargs)

File "funasr\auto\auto_model.py", line 281, in build_model

assert model_class is not None, f'{kwargs["model"]} is not registered'

AssertionError: FunASRNano is not registered

Traceback (most recent call last):
File "videotrans\task\job.py", line 105, in run
File "videotrans\task\_speech2text.py", line 159, in recogn
File "videotrans\recognition\__init__.py", line 246, in run
File "videotrans\recognition\_base.py", line 143, in run
File "videotrans\recognition\_funasr.py", line 64, in _exec
File "videotrans\configure\_base.py", line 289, in _new_process
RuntimeError: Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 898, in funasr_mlt
File "funasr\auto\auto_model.py", line 135, in init

model, kwargs = self.build_model(**kwargs)

File "funasr\auto\auto_model.py", line 281, in build_model

assert model_class is not None, f'{kwargs["model"]} is not registered'

AssertionError: FunASRNano is not registered
TaskCfgSTT(is_cuda=True, uuid='7b04c8cb75', cache_folder='D:/hai/AI/win-pyvideotrans/tmp/19868/7b04c8cb75', target_dir='D:/hai/AI/win-pyvideotrans/output/recogn', 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:/hai/AI/win-pyvideotrans/output/recogn/七哥 3月31日 全程无广.srt', target_wav=None, target_wav_output=None, name='d:/Downloads/七哥 3月31日 全程无广.mp4', noextname='七哥 3月31日 全程无广', basename='七哥 3月31日 全程无广.mp4', ext='mp4', dirname='D:/Downloads', shound_del_name=None, detect_language='zh-cn', recogn_type=3, model_name='Fun-ASR-Nano-2512', shibie_audio='D:/hai/AI/win-pyvideotrans/tmp/19868/7b04c8cb75/七哥 3月31日 全程无广-1774977774.1855414.wav', remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=True)


=
system:Windows-10-10.0.19045-SP0
version:v3.98
frozen:True
language:zh
root_dir:D:/hai/AI/win-pyvideotrans

1 Replies

这是由于阿里FunASR本地模型加载失败导致的。错误信息显示 FunASRNano is not registered,表明软件无法找到或注册指定的FunASR模型。

解决方案:

  1. 切换语音识别渠道:这是最直接的解决方法。请暂时不要使用“阿里FunASR(本地)”渠道。

    • 对于中文视频,建议改用“Qwen-ASR(本地)”渠道。
    • 或者使用“faster-whisper(本地)”渠道,并选择 large-v3 模型(需确保有足够显存或内存)。
  2. 检查模型文件:如果坚持使用FunASR渠道,请确保模型文件已正确下载。

    • 模型文件应位于软件根目录下的 models 文件夹内。
    • 检查是否存在与 Fun-ASR-Nano-2512 相关的模型文件夹。如果缺失,可能需要手动下载或通过配置网络代理后让软件自动下载。
  3. 配置网络代理:模型下载失败常因网络问题。如果你在中国大陆,请尝试在软件主界面的“网络代理地址”中填写可用的代理地址(如 http://127.0.0.1:10808),然后重启软件再试。

注意:此错误可能与特定版本的FunASR库兼容性问题有关。如果上述方法无效,建议优先采用方案1,切换至其他更稳定的语音识别渠道。

请查阅相关文档:

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.

Related resource