#8198 The maximum decoding length must be > 0:Traceback (most recent call last): File

47.121**5 Posted at: 1 hour ago

The maximum decoding length must be > 0:Traceback (most recent call last):
File "videotrans\process\stt_faster.py", line 139, in faster_whisper
File "faster_whisper\transcribe.py", line 1851, in restore_speech_timestamps
File "faster_whisper\transcribe.py", line 1213, in generate_segments
File "faster_whisper\transcribe.py", line 1446, in generate_with_fallback
ValueError: The maximum decoding length must be > 0

Traceback (most recent call last):
File "videotrans\task\only_one.py", line 71, in run
File "videotrans\task\_stage_recogn.py", line 63, in recogn
File "videotrans\recognition\__init__.py", line 141, in run
File "videotrans\recognition\_base.py", line 101, in run
File "videotrans\recognition\_whisper.py", line 39, in _exec
File "videotrans\recognition\_whisper.py", line 136, in _faster
File "videotrans\configure\base.py", line 277, in _new_process
videotrans.configure.excepts.VideoTransError: The maximum decoding length must be > 0:Traceback (most recent call last):
File "videotrans\process\stt_faster.py", line 139, in faster_whisper
File "faster_whisper\transcribe.py", line 1851, in restore_speech_timestamps
File "faster_whisper\transcribe.py", line 1213, in generate_segments
File "faster_whisper\transcribe.py", line 1446, in generate_with_fallback
ValueError: The maximum decoding length must be > 0

trk=[TransCreate]: uuid='5c49623d41', 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: C:/Users/admin/Desktop/THC560/THC560 桑德维克AXERA DD310 - DD311 - 第三部分.mp4,
输出结果保存到文件夹: C:/Users/admin/Desktop/THC560/_video_out/THC560 桑德维克AXERA DD310 - DD311 - 第三部分-mp4,
临时文件夹: D:/BaiduNetdiskDownload/win-pyvideotrans-v4.16/tmp/6396/5c49623d41
已选 清理已存在
已启用CUDA加速
未选 降噪
语音识别:faster-whisper(内置), large-v3-turbo, 发音语言: 西班牙语(拉美),
翻译渠道:DeepSeek,原始语言:西班牙语(拉美),目标语言:简体中文, 已选 发送完整字幕
配音渠道:Edge-TTS(免费), 角色:Yunyang(Male/CN), 配音语言:简体中文, 未选 二次语音识别
音量:+0%, 语速:+0%, 已选 音频加速, 未选 视频慢速
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: 嵌入硬字幕 , precent=4, 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=1685566


=
system:Windows-10-10.0.20348-SP0
version:v4.16
frozen:True
language:zh_CN
root_dir:D:/BaiduNetdiskDownload/win-pyvideotrans-v4.16

1 Replies

#1 DeepSeek reply at 1 hour ago

知识库中没有该精确报错的直接记录;根据日志可定位到 faster-whisper 识别阶段(restore_speech_timestamps 解码时),优先排查所用模型 large-v3-turbo 是否下载不完整/文件损坏,而不是翻译或配音渠道的问题。

处理步骤:

  1. 关闭软件,进入软件安装目录下的 models 文件夹,找到 models--mobiuslabsgmbh--faster-whisper-large-v3-turbo 目录,删除其中已下载的模型文件。
  2. 重新启动软件并再次执行识别,让软件重新下载该模型;如果自动下载仍失败,请参考手动下载地址覆盖模型文件。
  3. 若重下后仍报错,可在语音识别渠道中临时切换为其他模型(如 large-v3、medium)排除模型兼容性问题。
  4. 如果问题仅出现在这一个视频,可先尝试用格式转换工具将该视频转为标准 H.264/MP4 后再导入。

若以上操作后仍失败,请提供软件安装目录下 logs/ 文件夹中最新的日志文件(复制底部约30行报错信息),以便进一步定位。

请查阅相关文档:

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