#6085 语音识别阶段出错[faster-whisper(本地内置)] Subprocess Error: Backend should be defined in the BACKENDS_MAPPING. Offending backend: t

210.79* Posted at: 21 hours ago

语音识别阶段出错[faster-whisper(本地内置)] Subprocess Error: Backend should be defined in the BACKENDS_MAPPING. Offending backend: tensorflow_text
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\_whisper.py", line 40, in _exec

File "videotrans\recognition\_whisper.py", line 128, in _faster

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

videotrans.configure.excepts.VideoTransError: Subprocess Error: Backend should be defined in the BACKENDS_MAPPING. Offending backend: tensorflow_text
cfg=TaskCfgSTT(uuid='b7907be675', name="C:/Users/LiBo/Desktop/100 Players Simulate Minecraft's Deadliest Tournament!.mp4", dirname='C:/Users/LiBo/Desktop', noextname="100 Players Simulate Minecraft's Deadliest Tournament!", basename="100 Players Simulate Minecraft's Deadliest Tournament!.mp4", ext='mp4', target_dir='d:/program files/win-pyvideotrans/output/recogn', cache_folder='D:/Program Files/Win-Pyvideotrans/tmp/15960/b7907be675', 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:/program files/win-pyvideotrans/output/recogn/100 Players Simulate Minecraft's Deadliest Tournament!.srt", target_wav=None, target_wav_output=None, detect_language='auto', recogn_type=0, model_name='distil-large-v3', shibie_audio="D:/Program Files/Win-Pyvideotrans/tmp/15960/b7907be675/100 Players Simulate Minecraft's Deadliest Tournament!-1785034262.5177217.wav", remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=1, fix_punc=0)

1 Replies

这是由于升级到 v4.05/v4.06 后,transformers 库版本与旧代码残留文件冲突导致的 tensorflow_text 后端映射错误。

解决方案:

  1. 关闭软件。
  2. 前往官方下载页面,获取当前最新版本的完整包(约 2.6GB,非补丁包),全量解压到一个新的目录(例如 D:\pyVideoTrans)。
  3. 如果你之前已有配置文件(videotrans/params.json 等),可将其复制到新目录的同路径下以保留设置。
  4. 重新启动新目录下的 sp.exe
注意:文件名中带有 ! 等特殊符号,虽然通常不影响 FFmpeg 处理,但为减少潜在问题,建议将输入视频文件名改为纯英文数字(如 test.mp4)。
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

Dondate via PayPal

Related resource