#3107 TaskCfg(cache_folder='D:/ps/tmp/23464/10905034aa', target_dir='F:/张锦涛/_video_out/测试-mp4', remove_noise=True, is_separate

2408:8226* Posted at: 12 hours ago 👁9

语音识别阶段出错 [字节语音大模型极速版] 未知错误
Traceback (most recent call last):
File "videotrans\task\job.py", line 113, in run
File "videotrans\task\trans_create.py", line 365, in recogn
File "videotrans\recognition\__init__.py", line 208, in run
File "videotrans\recognition\_base.py", line 80, in run
File "videotrans\recognition\_zijiemodel.py", line 75, in _exec
RuntimeError: 未知错误

TaskCfg(cache_folder='D:/ps/tmp/23464/10905034aa', target_dir='F:/张锦涛/_video_out/测试-mp4', remove_noise=True, is_separate=False, detect_language='zh-cn', subtitle_language=None, source_language='简体中文', target_language='英语', source_language_code='zh-cn', target_language_code='en', source_sub='F:/张锦涛/_video_out/测试-mp4/zh-cn.srt', target_sub='F:/张锦涛/_video_out/测试-mp4/en.srt', source_wav='D:/ps/tmp/23464/10905034aa/remove_noise.wav', source_wav_output='F:/张锦涛/_video_out/测试-mp4/zh-cn.m4a', target_wav='D:/ps/tmp/23464/10905034aa/target.wav', target_wav_output='F:/张锦涛/_video_out/测试-mp4/en.m4a', subtitles='', novoice_mp4='D:/ps/tmp/23464/10905034aa/novoice.mp4', noextname='测试', shibie_audio=None, targetdir_mp4='F:/张锦涛/_video_out/测试-mp4/测试.mp4', instrument=None, vocal=None, back_audio='', background_music=None, app_mode='tiqu', subtitle_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='No', copysrt_rawvideo=False, clear_cache=False, translate_type=0, tts_type=0, recogn_type=7, model_name='large-v3', split_type=1, voice_autorate=False, video_autorate=True, cuda=False, name='F:/张锦涛/测试.mp4', basename='测试.mp4', ext='mp4', dirname='F:/张锦涛', shound_del_name=None, uuid='10905034aa', remove_silent_mid=False, align_sub_audio=True, enable_diariz=False, nums_diariz=0, rephrase=2, only_out_mp4=False)


=
system:Windows-10-10.0.19045-SP0
version:v3.92
frozen:True
language:zh
root_dir:D:/ps

1 Replies

这是由于使用字节语音大模型极速版进行语音识别时,API调用失败导致的未知错误。

解决方案:

  1. 检查API配置:确保在“语音识别渠道”设置中,为“字节语音大模型极速版”正确填写了有效的API Key和App ID。
  2. 检查网络连接:字节火山引擎API需要稳定的网络连接。如果在中国大陆使用,请确保网络可以正常访问其服务。
  3. 查看官方文档:字节火山语音识别API可能有调用频率限制或特定格式要求。请参考官方文档确认音频格式(如采样率、编码)是否符合要求。
  4. 尝试其他识别渠道:作为临时解决方案,可以切换到其他语音识别渠道,例如“faster-whisper(本地)”或“Edge-TTS(在线)”,以确认是否是特定于字节渠道的问题。
  5. 检查音频文件:日志显示处理的是降噪后的音频 remove_noise.wav。请确认该文件存在且未被损坏。

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