#8539 ChatterBox-TTS dubbing errorTraceback (most recent call last):

138.219**0 Posted at: 2 hours ago

ChatterBox-TTS dubbing error
Traceback (most recent call last):
File "videotrans\task\only_one.py", line 108, in run
File "videotrans\task\_stage_dubbing.py", line 24, in dubbing
File "videotrans\task\_stage_dubbing.py", line 101, in _tts
File "videotrans\tts\__init__.py", line 132, in run
File "videotrans\tts\_base.py", line 98, in run
File "videotrans\tts\_chatterbox.py", line 97, in _exec
videotrans.configure.excepts.DubbingSrtError: ChatterBox-TTS dubbing error

trk=[TransCreate]: uuid='81a239acfb', proxy_str=None, cfg=[TaskCfgVTT]当前工作模式: 翻译视频单视频模式
原始输入文件名: E:/Filme dublado/A Cidade Mais Perigosa da Internet.mp4,
输出结果保存到文件夹: E:/Filme dublado/_video_out/A Cidade Mais Perigosa da Internet-mp4,
临时文件夹: E:/win-pyvideotrans-v4.17-1028/tmp/8920/81a239acfb
未选清理已存在
已启用CUDA加速
STT Service:faster-whisper(Built-in), distil-large-v3, 发音语言: English, , 数据类型:default
TranslateSrt:Microsoft Translate (Free),原始语言:English,目标语言:Portuguese (Brazilian), 已选 SendSRT, settings.get('trans_thread')=5, settings.get('aitrans_thread')=40
TTS Service:ChatterBox(Built-in), 角色:clone, 配音语言:Portuguese (Brazilian)
音量:+0%, 语速:+0%, 未选音频加速, 未选视频慢速
未选移除字幕间空隙, 已选强制对齐字幕和声音
已选移除每条字幕配音开头和结尾静音缓冲
静音移除力度: default
字幕: No Subtitles
已选仅输出mp4, precent=15, hasend=False, should_recogn=True, should_trans=True, should_dubbing=True, should_hebing=True, is_copy_video=True, video_codec_num=264, ignore_align=False, is_audio_trans=False, clone_ref='', should_recogn2=False, do_diarize=True
video_duration_ms=1199781

=
system:Windows-10-10.0.19045-SP0
version:v4.17
frozen:True
language:en_US
root_dir:E:/win-pyvideotrans-v4.17-1028

#1 DeepSeek reply at 2 hours ago

This error is only the top-level wrapper DubbingSrtError; it does not include the underlying cause, so it cannot be pinpointed from the text alone. For ChatterBox, the usual causes are, in order: (1) the two extra data files required by the channel were not downloaded; (2) the model files are incomplete; (3) the clone reference audio is invalid; (4) CUDA / VRAM problems.

Check in the following order:

Check the two extra files required by ChatterBox (most common cause)
- Open E:/win-pyvideotrans-v4.17-1028/models/pkuser_home/
- Confirm that features.msgpack and weights.npz exist. If they do not exist, or the folder does not exist, download https://github.com/explosion/spacy-pkuseg/releases/download/v0.0.26/spacy_ontonotes.zip, unzip it, then create the pkuser_home folder and copy both files into it.
- ChatterBox is also downloadable through huggingface.co, so it is common for the download to fail even if github.com is reachable. Make sure the network can reach github.com when downloading the model for the first time.
Check the model files
- Confirm E:/win-pyvideotrans-v4.17-1028/models/models--ResembleAI--chatterbox contains complete model files.
- If it is incomplete, delete that directory and rerun the task (or download it manually from https://huggingface.co/ResembleAI/chatterbox/tree/main and place it there).
Check the clone reference audio
- You selected 角色: clone; this channel extracts the reference audio from the original video, so its quality is uncontrollable.
- Go to Menu → Tools → Advanced Options → Speech Recognition (ASR) and set Min Speech Duration (ms) to 3000 or greater; the reference audio must be at least 3 seconds long. Also set Max Speech Duration (s) to 10.
- Rename the video file to a short English name with no spaces: E:/Filme dublado/A Cidade Mais Perigosa da Internet.mp4 contains spaces and deep folders; move it to E:/video1.mp4 and retry. This avoids ffmpeg path problems that are reported by the TTS stage.
Test the channel
- Switch the TTS channel to Edge-TTS (Free) and run the same video; if Edge-TTS also fails, the problem is in the dubbing/alignment stage, not ChatterBox itself. If Edge-TTS succeeds, the problem is definitely in ChatterBox's model files or the reference audio.
CUDA / VRAM
- You have CUDA acceleration enabled. ChatterBox is a 4B-level model, so VRAM out-of-memory usually throws an OOM or BrokenProcessPool error. If you have less than 8GB VRAM, try unchecking CUDA Acceleration.

If the above steps do not resolve the problem, the specific cause cannot be determined for now. Go to E:/win-pyvideotrans-v4.17-1028/logs/ and find the latest log file for the day. Copy the last 30 lines around the error (the log level is DEBUG, so it contains more detail than the dialog), and provide it so it can be analyzed.

#8539 ChatterBox-TTS dubbing errorTraceback (most recent call last):

1 Replies

Please refer to the related documentation:

Post Your Reply

Related resource