#7758 1.mp4No subtitles recognized. Check: [1] Media contains clear human speech, [2] Selected spoken language matches audio,

2a01**1 Posted at: 1 hour ago

1.mp4No subtitles recognized. Check: [1] Media contains clear human speech, [2] Selected spoken language matches audio, [3] Selected engine supports spoken language.
Traceback (most recent call last):
File "videotrans\task\only_one.py", line 70, in run
File "videotrans\task\_stage_recogn.py", line 76, in recogn
videotrans.configure.excepts.SpeechToTextError: 1.mp4No subtitles recognized. Check: [1] Media contains clear human speech, [2] Selected spoken language matches audio, [3] Selected engine supports spoken language.

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/ALI/Desktop/1.mp4,
输出结果保存到文件夹: C:/Users/ALI/Desktop/_video_out/1-mp4,
临时文件夹: D:/win-pyvideotrans-v4.14/tmp/18028/d5ac7a8d09
已选清理已存在
未启用CUDA加速
未选降噪
STT Service:Dolphin Asian(Built-in), , 发音语言: English, 断句方式:默认断句
TranslateSrt:Google Translate (Free),原始语言:English,目标语言:Persian, 已选 SendSRT
TTS Service:Edge-TTS (Free), 角色:Farid(Male/IR), 配音语言:Persian, 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
字幕: Hard Subtitles
代理地址:http://127.0.0.1:2080
video_duration_ms=81433

=
system:Windows-10-10.0.26300-SP0
version:v4.14
frozen:True
language:en_US
root_dir:D:/win-pyvideotrans-v4.14

#1 DeepSeek reply at 1 hour ago

The error means the ASR engine returned no subtitle lines.

In your cfg the mismatch is the main cause: you selected spoken language English, but the ASR channel Dolphin Asian (Built-in) is designed for Asian languages (40+ Asian languages and 20 Chinese dialects) and may not properly handle English.

This makes ASR fail or return empty.

Fix:

Switch the STT Service to a channel that supports English, e.g.

faster-whisper(Built-in) with model large-v3 or large-v3-turbo, or openai-whisper(Built-in).
Keep Spoken language as English.
Confirm the source 1.mp4 really contains clear human speech (not only BGM/noise).
Re-run with 清理已生成(Clear Output) selected.
If it still returns empty, try enabling 分离人声背景声(Separate Vocal/BGM) in 设置更多参数(More...) to remove background noise, then retry.

Also note: without CUDA acceleration, local Whisper models run on CPU and will be slow; enable CUDA only if you have an NVIDIA GPU with CUDA 12.8 and cuDNN 9 properly installed.

#7758 1.mp4No subtitles recognized. Check: [1] Media contains clear human speech, [2] Selected spoken language matches audio,

1 Replies

请查阅相关文档：

Post Your Reply

Related resource