#3176 TaskCfg(cache_folder='D:/win-videotrans-v3.67-tiny/tmp/31412/speech2text', target_dir='e:/doc/pyvideo/recogn', remove_no

45.139* Posted at: 7 days ago 👁31

语音识别阶段出错:[faster-whisper(本地)] 运行时错误:Traceback (most recent call last):
File "videotrans\process\_overall.py", line 93, in run
File "faster_whisper\transcribe.py", line 689, in init

valid_keys = signature(FeatureExtractor.__init__).parameters.keys()

ValueError: Requested int8_float32 compute type, but the target device or backend do not support efficient int8_float32 computation.
:
Traceback (most recent call last):
File "videotrans\task\job.py", line 113, in run
File "videotrans\task\_speech2text.py", line 146, in recogn
File "videotrans\recognition\__init__.py", line 239, in run
File "videotrans\recognition\_base.py", line 80, in run
File "videotrans\recognition\_overall.py", line 182, in _exec
RuntimeError: Traceback (most recent call last):
File "videotrans\process\_overall.py", line 93, in run
File "faster_whisper\transcribe.py", line 689, in init

valid_keys = signature(FeatureExtractor.__init__).parameters.keys()

ValueError: Requested int8_float32 compute type, but the target device or backend do not support efficient int8_float32 computation.

TaskCfg(cache_folder='D:/win-videotrans-v3.67-tiny/tmp/31412/speech2text', target_dir='e:/doc/pyvideo/recogn', remove_noise=False, is_separate=False, detect_language='zh-cn', subtitle_language=None, source_language=None, target_language=None, source_language_code=None, target_language_code=None, source_sub=None, target_sub='e:/doc/pyvideo/recogn/独家四维模型,5 分钟理解做私域底层逻辑_1.srt', source_wav=None, source_wav_output=None, target_wav=None, target_wav_output=None, subtitles=None, novoice_mp4=None, noextname='独家四维模型,5 分钟理解做私域底层逻辑_1', shibie_audio='D:/win-videotrans-v3.67-tiny/tmp/31412/speech2text/独家四维模型,5 分钟理解做私域底层逻辑_1-1770611002.42887.wav', targetdir_mp4=None, instrument=None, vocal=None, back_audio=None, background_music=None, app_mode='biaozhun', subtitle_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role=None, copysrt_rawvideo=False, clear_cache=False, translate_type=None, tts_type=None, recogn_type=0, model_name='large-v3-turbo', split_type=0, voice_autorate=False, video_autorate=False, cuda=True, name='E:/Downloads/独家四维模型,5 分钟理解做私域底层逻辑_1.mp4', basename='独家四维模型,5 分钟理解做私域底层逻辑_1.mp4', ext='mp4', dirname='E:/Downloads', shound_del_name=None, uuid='bd9e3171f1', remove_silent_mid=False, align_sub_audio=True, enable_diariz=False, nums_diariz=0, rephrase=0, only_out_mp4=False)


=
system:Windows-10-10.0.19045-SP0
version:v3.90
frozen:True
language:zh
root_dir:D:/win-videotrans-v3.67-tiny

3 Replies

这是由于 faster-whisper 模型在您的硬件上不支持 int8_float32 计算类型导致的。错误信息明确指出:“Requested int8_float32 compute type, but the target device or backend do not support efficient int8_float32 computation.”

解决方案:

  1. 在软件主界面,点击菜单栏的“工具” -> “高级选项”。
  2. 在“通用设置”选项卡中,找到“faster-whisper 计算类型”设置项。
  3. 将该选项从 int8_float32 更改为 float16float32
  4. 点击“保存”并重启软件,然后重新尝试语音识别任务。

如果更改后问题依旧,或者您的显卡不支持 CUDA 加速,请尝试以下步骤:

  1. 在“高级选项”的“通用设置”中,取消勾选“启用CUDA加速”。
  2. 将“faster-whisper 计算类型”设置为 float32
  3. 保存并重启软件。

请查阅相关文档:

预处理阶段出错:运行时错误:opening input: No such file or directory opening input file E:/Downloads/99%25 的知识付费业务,第一天就注定赚不_1.mp4. opening input files: No such file or directory:
Traceback (most recent call last):
File "videotrans\util\help_ffmpeg.py", line 364, in runffmpeg
File "subprocess.py", line 524, in run
subprocess.CalledProcessError: Command '['ffmpeg', '-hide_banner', '-ignore_unknown', '-threads', '0', '-y', '-i', 'E:/Downloads/99%25 的知识付费业务,第一天就注定赚不_1.mp4', '-ac', '1', '-ar', '16000', '-c:a', 'pcm_s16le', 'D:/win-videotrans-v3.67-tiny/tmp/31412/speech2text/99%25 的知识付费业务,第一天就注定赚不_1-1770611476.3906512.wav']' returned non-zero exit status 4294967294.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "videotrans\task\job.py", line 67, in run
File "videotrans\task\_speech2text.py", line 55, in prepare
File "videotrans\util\help_ffmpeg.py", line 783, in conver_to_16k
File "videotrans\util\help_ffmpeg.py", line 410, in runffmpeg
RuntimeError: opening input: No such file or directory opening input file E:/Downloads/99%25 的知识付费业务,第一天就注定赚不_1.mp4. opening input files: No such file or directory

TaskCfg(cache_folder='D:/win-videotrans-v3.67-tiny/tmp/31412/speech2text', target_dir='e:/doc/pyvideo/recogn', remove_noise=False, is_separate=False, detect_language='zh-cn', subtitle_language=None, source_language=None, target_language=None, source_language_code=None, target_language_code=None, source_sub=None, target_sub='e:/doc/pyvideo/recogn/99%25 的知识付费业务,第一天就注定赚不_1.srt', source_wav=None, source_wav_output=None, target_wav=None, target_wav_output=None, subtitles=None, novoice_mp4=None, noextname='99%25 的知识付费业务,第一天就注定赚不_1', shibie_audio='D:/win-videotrans-v3.67-tiny/tmp/31412/speech2text/99%25 的知识付费业务,第一天就注定赚不_1-1770611476.3906512.wav', targetdir_mp4=None, instrument=None, vocal=None, back_audio=None, background_music=None, app_mode='biaozhun', subtitle_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role=None, copysrt_rawvideo=False, clear_cache=False, translate_type=None, tts_type=None, recogn_type=0, model_name='large-v3', split_type=0, voice_autorate=False, video_autorate=False, cuda=False, name='E:/Downloads/99%25 的知识付费业务,第一天就注定赚不_1.mp4', basename='99%25 的知识付费业务,第一天就注定赚不_1.mp4', ext='mp4', dirname='E:/Downloads', shound_del_name=None, uuid='eb8d7af326', remove_silent_mid=False, align_sub_audio=True, enable_diariz=False, nums_diariz=0, rephrase=0, only_out_mp4=False)

system:Windows-10-10.0.19045-SP0
version:v3.90
frozen:True
language:zh
root_dir:D:/win-videotrans-v3.67-tiny

这是由于输入的视频文件路径包含特殊字符(%)导致 FFmpeg 无法正确读取文件。错误信息显示:“No such file or directory opening input file E:/Downloads/99%25 的知识付费业务,第一天就注定赚不_1.mp4”。

解决方案:

  1. 重命名源视频文件,移除文件名中的所有特殊字符,特别是 % 符号。例如,将 99%25 的知识付费业务,第一天就注定赚不_1.mp4 重命名为 知识付费业务,第一天就注定赚不_1.mp4
  2. 确保文件路径不包含中文、空格或特殊符号。最佳实践是将视频文件移动到纯英文路径下,例如 E:\video\test.mp4
  3. 重新启动 pyVideoTrans 软件,并选择重命名后或移动后的视频文件进行处理。

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