#8240 No human voice detected. Please confirm that human speech is present in the original file. [info.duration_after_vad=0.83

86.249**9 Posted at: 1 hour ago

No human voice detected. Please confirm that human speech is present in the original file. [info.duration_after_vad=0.832s].
_kw={'beam_size': 5, 'best_of': 5, 'condition_on_previous_text': False, 'threshold': 0.45, 'no_speech_threshold': 0.6, 'temperature': 0.0, 'repetition_penalty': 1.0, 'compression_ratio_threshold': 2.4, 'initial_prompt': None}
info=TranscriptionInfo(language='en', language_probability=1, duration=338.4773125, duration_after_vad=0.832, all_language_probs=None, transcription_options=TranscriptionOptions(beam_size=5, best_of=5, patience=1, length_penalty=1, repetition_penalty=1.0, no_repeat_ngram_size=0, log_prob_threshold=-1.0, no_speech_threshold=0.6, compression_ratio_threshold=2.4, condition_on_previous_text=False, prompt_reset_on_temperature=0.5, temperatures=[0.0], initial_prompt=None, prefix=None, suppress_blank=True, suppress_tokens=(1, 2, 7, 8, 9, 10, 14, 25, 26, 27, 28, 29, 31, 58, 59, 60, 61, 62, 63, 90, 91, 92, 93, 359, 503, 522, 542, 873, 893, 902, 918
......
59, 503, 522, 542, 873, 893, 902, 918, 922, 931, 1350, 1853, 1982, 2460, 2627, 3246, 3253, 3268, 3536, 3846, 3961, 4183, 4667, 6585, 6647, 7273, 9061, 9383, 10428, 10929, 11938, 12033, 12331, 12562, 13793, 14157, 14635, 15265, 15618, 16553, 16604, 18362, 18956, 20075, 21675, 22520, 26130, 26161, 26435, 28279, 29464, 31650, 32302, 32470, 36865, 42863, 47425, 49870, 50254, 50258, 50358, 50359, 50360, 50361, 50362), without_timestamps=False, max_initial_timestamp=1.0, word_timestamps=True, prepend_punctuations='"\'“¿([{-', append_punctuations='"\'.。,，!！?？:：”)]}、', multilingual=False, max_new_tokens=None, clip_timestamps=[0.0], hallucination_silence_threshold=None, hotwords=''), vad_options=VadOptions(threshold=0.45, neg_threshold=None, min_speech_duration_ms=0, max_speech_duration_s=inf, min_silence_duration_ms=2000, speech_pad_ms=400))

trk=[TransCreate]: uuid='605ffa75b5', 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/bureau-r/Downloads/Video/Guns N' Roses Knockin' On Heaven's Door (videoclip) HD.mp4,
输出结果保存到文件夹: C:/Users/bureau-r/Downloads/Video/_video_out/Guns N' Roses Knockin' On Heaven's Door (videoclip) HD-mp4,
临时文件夹: C:/Users/bureau-r/Desktop/win-pyvideotrans-v4.16/tmp/2304/605ffa75b5
已选清理已存在
未启用CUDA加速
未选降噪
STT Service:faster-whisper(Built-in), small, 发音语言: English,
TranslateSrt:Google Translate (Free),原始语言:English,目标语言:French, 已选 SendSRT
TTS Service:Edge-TTS (Free), 角色:Denise(Female/FR), 配音语言:French, 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: Hard Subtitles
已选仅输出mp4, 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=338477

=
system:Windows-10-10.0.19044-SP0
version:v4.16
frozen:True
language:en_US
root_dir:C:/Users/bureau-r/Desktop/win-pyvideotrans-v4.16

#1 DeepSeek reply at 1 hour ago

Root cause: VAD (voice activity detection) only recognized 0.832 seconds of speech out of a 338-second file, so no subtitle segment was produced and the task aborted.

The VAD statistics (threshold=0.45, min_silence_duration_ms=2000) show that the vocals in this music video are buried in the backing track, and the VAD classifier therefore judged almost the whole file as "non-speech".

Fix with the following steps, in order:

Separate the vocals from the background music (the most important step)
On the main interface, click More... (设置更多参数) and check Separate Vocal/BGM (分离人声背景声). This isolates the vocals from the music, which makes them detectable by VAD and ASR. You may also check Re-embed BGM (重新嵌入背景声) to mix the music back in afterwards.
Lower the VAD speech threshold
Go to Menu → Tools/Options → Advanced Options → ASR Settings:
- VAD: Speech probability threshold (语音阈值): change from the default 0.45 to 0.2~0.3 (lower values are more sensitive).
- Leave VAD:min speech duration(ms) at 3000, and keep max speech duration(s) around 5.
Rename the source file to a simple name
The current path contains an apostrophe (Guns N' Roses ...), which FFmpeg handles poorly. Rename it to something like D:/videos/gnr.mp4 and move it to a shallow, ASCII-only path.
Rerun the task
Keep Clear Output (清理已生成) checked to avoid reusing the failed cache, then restart the task.

If you still get duration_after_vad close to 0 after separation, run the Speech-to-Text panel on the same file with Separate Vocal/BGM checked to confirm whether usable speech exists in the audio at all. A pure instrumental/music-only file cannot be processed by this tool.

#8240 No human voice detected. Please confirm that human speech is present in the original file. [info.duration_after_vad=0.83

1 Replies

请查阅相关文档：

Post Your Reply

Related resource