#8740 Error during subtitle translation stage [M2M100(Built-in)] System Error (None): NoneTraceback (most recent call last):

212.180**4 Posted at: 18 hours ago

Error during subtitle translation stage [M2M100(Built-in)] System Error (None): None
Traceback (most recent call last):
File "videotrans\task\only_one.py", line 113, in run
File "videotrans\task\_stage_translate.py", line 31, in trans
File "videotrans\translator\_runner.py", line 71, in run
File "videotrans\translator\_base.py", line 74, in run
File "videotrans\translator\_m2m100.py", line 35, in _download
File "sentencepiece\__init__.py", line 468, in Init
File "sentencepiece\__init__.py", line 961, in Load
File "sentencepiece\__init__.py", line 316, in LoadFromFile
OSError: Not found: "C:/Users/Кончинесса/Downloads/win-pyvideotrans-v4.18-1106/models/m2m100_12b/sentencepiece.model": No such file or directory Error #2

trk=Translation V/A 单视频模式
Select Media File: D:/Видео/IMG_7853.MOV,
Output Directory: D:/Видео/IMG_7853-mov,
self.cfg.cache_folder='C:/Users/Кончинесса/Downloads/win-pyvideotrans-v4.18-1106/tmp/14792/628577bca1'
Selected Clear Output, Not-Selected Enable CUDA
STT Service:faster-whisper(Built-in), large-v3-turbo, Spoken: Russian
Max Speech Duration (s): 5s
Min Speech Duration (ms): 3000ms
Min Silence Duration for Split (ms): 600ms
VAD Speech Threshold: 0.45
VAD Engine: silero
Compute Type:default
Beam Size:5
Best Of:5
Condition on Previous Text:False
Repetition Penalty:1.0
Compression Ratio Threshold:2.4
TranslateSrt:M2M100(Built-in),Spoken:Russian,Target:English
Traditional Translation Batch Size (Lines): 5
TTS Service:Qwen3-TTS(Built-in), Voices:clone, Target:English
Volume:+0%, Speed:+0%, Selected TTS Speedup, Not-Selected Slow Video
Selected Trim Start/End Silence in Dubbed Segments
Silence Removal Intensity: default
No Subtitles
video duration:680400ms
video information:{'video_fps': 30.0, 'r_frame_rate': 30.0, 'video_codec_name': 'hevc', 'audio_codec_name': 'aac', 'width': 1920, 'height': 1080, 'time': 680400, 'streams_len': 2, 'streams_audio': 1, 'video_streams': 1, 'color': 'yuv420p'}
self.cfg=TaskCfgVTT(uuid='628577bca1', name='D:/Видео/IMG_7853.MOV', dirname='D:/Видео', noextname='IMG_7853', basename='IMG_7853.MOV', ext='mov', target_dir='D:/Видео/IMG_7853-mov', cache_folder='C:/Users/Кончинесса/Downloads/win-pyvideotrans-v4.18-1106/tmp/14792/628577bca1', is_cuda=False, source_language='Russian', source_language_code='ru', source_sub='D:/Видео/IMG_7853-mov/ru.srt', source_wav='C:/Users/Кончинесса/Downloads/win-pyvideotrans-v4.18-1106/tmp/14792/628577bca1/ru.wav', source_wav_output='D:/Видео/IMG_7853-mov/ru.m4a', target_language='English', target_language_code='en', target_sub='D:/Видео/IMG_7853-mov/en.srt', target_wav='C:/Users/Кончинесса/Downloads/win-pyvideotrans-v4.18-1106/tmp/14792/628577bca1/target.wav', target_wav_output='D:/Видео/IMG_7853-mov/en.m4a', translate_type=2, tts_type=1, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='clone', voice_autorate=True, video_autorate=False, remove_silent_mid=False, align_sub_audio=True, detect_language='ru', recogn_type=0, model_name='large-v3-turbo', shibie_audio=None, remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=False, fix_punc=0, app_mode='biaozhun', subtitle_language=None, targetdir_mp4='D:/Видео/IMG_7853-mov/IMG_7853.mp4', novoice_mp4='C:/Users/Кончинесса/Downloads/win-pyvideotrans-v4.18-1106/tmp/14792/628577bca1/novoice.mp4', is_separate=False, embed_bgm=True, instrument='C:/Users/Кончинесса/Downloads/win-pyvideotrans-v4.18-1106/tmp/14792/628577bca1/instrument.wav', vocal='C:/Users/Кончинесса/Downloads/win-pyvideotrans-v4.18-1106/tmp/14792/628577bca1/vocal.wav', clear_cache=True, background_music='', subtitle_type=0, only_out_mp4=False, recogn2pass=False, output_srt=0, copysrt_rawvideo=False, loop_backaudio=1, backaudio_volume=0.8, batch=False)
video_duration_ms=680400


=
system:Windows-10-10.0.26200-SP0
version:v4.18
frozen:True
language:en_US
root_dir:C:/Users/Кончинесса/Downloads/win-pyvideotrans-v4.18-1106

1 Replies

#1 DeepSeek reply at 18 hours ago

Cause

The M2M100 local model is incomplete or was not downloaded — the file models/m2m100_12b/sentencepiece.model does not exist, so loading the tokenizer fails directly with OSError: Not found. This is not a translation logic error, but a failed or interrupted model download.

Solution

Option 1: Manually download the complete model (recommended if you want to keep using M2M100)

  1. Download: https://modelscope.cn/models/himyworld/videotrans/resolve/master/m2m100_12b_model.zip
  2. Extract it and get the m2m100_12b folder.
  3. Put the entire m2m100_12b folder into software directory/models/, so that the final structure is:
    .../win-pyvideotrans-v4.18-1106/models/m2m100_12b/sentencepiece.model
  4. Make sure the folder contains all files (sentencepiece.model, config.json, weight files, etc.). If any are missing, extract again or redownload the zip.
  5. Restart the software and retry. Keep Clear Output checked to avoid reusing old cache.

Option 2: Switch translation channel (simplest, no download needed)

M2M100 is a local model with a large size and is prone to incomplete downloads. You do not need it for Russian→English translation:

  1. In Translation Services, change it to Google Translate (Free) (requires a proxy in mainland China), or DeepSeek (better quality, extremely low cost; fill in the key at Menu → Translation Settings → DeepSeek).
  2. Retry directly.

Additional note (important, may cause other errors)

Your software is installed at C:/Users/Кончинесса/Downloads/win-pyvideotrans-v4.18-1106, and the path contains the Cyrillic username Кончинесса, and it is in the Downloads folder. The knowledge base explicitly requires extracting the software to a short path with only English letters and digits, such as D:\pyvideotrans. Paths with non-ASCII characters can cause model download failures, ffmpeg call failures, and temporary file read/write errors. It is recommended to move the entire software folder to D:\pyvideotrans, then redo the model download or configuration.

Please refer to the related documentation:

Thinking...
Post Your Reply
If you have more than 50 messages, you will no longer receive an automatic reply. Please ask a new question!
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

Related resource