#4542 TaskCfgVTT(is_cuda=True, uuid='bc3fdb16e7', cache_folder='E:/AI/pyvideotrans/tmp/22136/bc3fdb16e7', target_dir='C:/Users

2408:8214* Posted at: 1 hour ago 👁12

语音识别阶段出错 [faster-whisper(本地)] Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 356, in faster_whisper
File "faster_whisper\transcribe.py", line 689, in init
ValueError: Requested int8_float16 compute type, but the target device or backend do not support efficient int8_float16 computation.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 367, in faster_whisper
File "faster_whisper\transcribe.py", line 689, in init
ValueError: Requested float16 compute type, but the target device or backend do not support efficient float16 computation.

Traceback (most recent call last):
File "videotrans\task\job.py", line 105, in run
File "videotrans\task\trans_create.py", line 390, in recogn
File "videotrans\recognition\__init__.py", line 293, in run
File "videotrans\recognition\_base.py", line 143, in run
File "videotrans\recognition\_overall.py", line 33, in _exec
File "videotrans\recognition\_overall.py", line 106, in _faster
File "videotrans\configure\_base.py", line 289, in _new_process
RuntimeError: Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 356, in faster_whisper
File "faster_whisper\transcribe.py", line 689, in init
ValueError: Requested int8_float16 compute type, but the target device or backend do not support efficient int8_float16 computation.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 367, in faster_whisper
File "faster_whisper\transcribe.py", line 689, in init
ValueError: Requested float16 compute type, but the target device or backend do not support efficient float16 computation.
TaskCfgVTT(is_cuda=True, uuid='bc3fdb16e7', cache_folder='E:/AI/pyvideotrans/tmp/22136/bc3fdb16e7', target_dir='C:/Users/56309/Videos/4K Video Downloader+/_video_out/How I Make Stylized Water for My Animated Series in Blender-mp4', source_language='英语', source_language_code='en', source_sub='C:/Users/56309/Videos/4K Video Downloader+/_video_out/How I Make Stylized Water for My Animated Series in Blender-mp4/en.srt', source_wav='E:/AI/pyvideotrans/tmp/22136/bc3fdb16e7/en.wav', source_wav_output='C:/Users/56309/Videos/4K Video Downloader+/_video_out/How I Make Stylized Water for My Animated Series in Blender-mp4/en.m4a', target_language='简体中文', target_language_code='zh-cn', target_sub='C:/Users/56309/Videos/4K Video Downloader+/_video_out/How I Make Stylized Water for My Animated Series in Blender-mp4/zh-cn.srt', target_wav='E:/AI/pyvideotrans/tmp/22136/bc3fdb16e7/target.wav', target_wav_output='C:/Users/56309/Videos/4K Video Downloader+/_video_out/How I Make Stylized Water for My Animated Series in Blender-mp4/zh-cn.m4a', name='C:/Users/56309/Videos/4K Video Downloader+/How I Make Stylized Water for My Animated Series in Blender.mp4', noextname='How I Make Stylized Water for My Animated Series in Blender', basename='How I Make Stylized Water for My Animated Series in Blender.mp4', ext='mp4', dirname='C:/Users/56309/Videos/4K Video Downloader+', shound_del_name=None, translate_type=3, tts_type=0, volume='+20%', pitch='+0Hz', voice_rate='+0%', voice_role='Xiaoxiao(Female/CN)', voice_autorate=False, video_autorate=True, remove_silent_mid=False, align_sub_audio=True, detect_language='en', recogn_type=0, model_name='large-v3-turbo', shibie_audio=None, remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False, subtitle_language=None, app_mode='biaozhun', subtitles='', targetdir_mp4='C:/Users/56309/Videos/4K Video Downloader+/_video_out/How I Make Stylized Water for My Animated Series in Blender-mp4/How I Make Stylized Water for My Animated Series in Blender.mp4', novoice_mp4='E:/AI/pyvideotrans/tmp/22136/bc3fdb16e7/novoice.mp4', is_separate=False, embed_bgm=False, instrument=None, vocal='E:/AI/pyvideotrans/tmp/22136/bc3fdb16e7/vocal.wav', back_audio='', clear_cache=False, background_music=None, subtitle_type=0, only_out_mp4=False, recogn2pass=False, output_srt=0, copysrt_rawvideo=False, loop_backaudio=1, backaudio_volume=0.8)


=
system:Windows-10-10.0.19044-SP0
version:v3.99
frozen:True
language:zh
root_dir:E:/AI/pyvideotrans

1 Replies

这是由于你的显卡不支持 faster-whisper 默认使用的 float16 或 int8_float16 加速模式。常见原因是显卡较老(如 GTX 10系及以下)、CUDA/cuDNN 版本不匹配,或驱动过旧。

解决方案(按推荐顺序尝试):

  1. 切换计算类型至 float32:在菜单栏 工具/选项 → 高级选项 → 语音识别参数 中,将 CUDA数据类型 改为 float32,然后重试。这会牺牲部分速度但兼容性更好。
  2. 回退到 CPU 模式:若仍然报错,在主界面取消勾选 CUDA加速,使用 CPU 处理(速度较慢)。
  3. 更新 CUDA 和 cuDNN:确保已安装 CUDA 12.8+ 和 cuDNN 9.11+,参见Windows上安装CUDA12.8和cuDNN9.11
  4. 更换小模型:在 faster-whisper(本地) 下改用 mediumsmall 模型,降低算力需求。

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