#7570 No human voice detected. Please confirm that human speech is present in the original file. [info.duration_after_vad=0.0s

200.164**5 Posted at: 1 hour ago

No human voice detected. Please confirm that human speech is present in the original file. [info.duration_after_vad=0.0s].
_kw={'beam_size': 5, 'best_of': 5, 'condition_on_previous_text': False, 'threshold': 1.0, 'no_speech_threshold': 1.0, 'temperature': 0.0, 'repetition_penalty': 1.0, 'compression_ratio_threshold': 2.4, 'initial_prompt': 'Translate spoken English into natural Brazilian Portuguese.\n\nRules:\n- Use conversational tone (casual, like YouTube tutorials)\n- Shorten sentences for speech timing\n- Adapt idioms and expressions naturally\n- Avoid literal translation\n- Prefer Brazilian informal speech (e.g., "clica", "abre", "vai em")\n- Keep it clear and direct\n\nOutput must sound like a real Brazilian explaining a tutorial.'}
info=TranscriptionInfo(language='en', language_probability=1, duration=1093.3973125, duration_after_vad=0.0, all_language_probs=None, transcription_options=TranscriptionOptions(beam_size=5, best_of=5, patience=1, length_penalty=1, repetition_penalty
......
speech (e.g., "clica", "abre", "vai em")\n- Keep it clear and direct\n\nOutput must sound like a real Brazilian explaining a tutorial.', 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, 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, 50359, 50360, 50361, 50362, 50363), 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=1.0, neg_threshold=None, min_speech_duration_ms=0, max_speech_duration_s=inf, min_silence_duration_ms=2000, speech_pad_ms=400))

cfg=[TaskCfgVTT]当前工作模式: 翻译视频 单视频模式
原始输入文件名: D:/CETP/CETP/CETP/Videos/5. Intro to Kernel Development/028 - Intro_to_Kernel_4 hide01.ir.mp4,
输出结果保存到文件夹: D:/CETP/CETP/CETP/Videos/5. Intro to Kernel Development/D/028 - Intro_to_Kernel_4 hide01.ir-mp4,
临时文件夹: C:/Users/JOHN/Documents/DUBLADOR/win-pyvideotrans-v4.13-1/tmp/14280/807be5dd8d
已选 清理已存在
已启用CUDA加速
未选 降噪
STT Service:faster-whisper(Built-in), large-v3-turbo, 发音语言: English, 断句方式:默认断句
TranslateSrt:Microsoft Translate (Free),原始语言:English,目标语言:Portuguese (Brazilian), 已选 SendSRT
TTS Service:Edge-TTS (Free), 角色:Antonio(Male/BR), 配音语言:Portuguese (Brazilian), 未选 二次语音识别
音量:+0%, 语速:-8%, 未选 音频加速, 已选 视频慢速
字幕: No Subtitles
已选 仅输出mp4
video_duration_ms=1093400


=
system:Windows-10-10.0.19045-SP0
version:v4.13
frozen:True
language:en_US
root_dir:C:/Users/JOHN/Documents/DUBLADOR/win-pyvideotrans-v4.13-1

1 Replies

#1 DeepSeek reply at 1 hour ago

The root cause is that the VAD (Voice Activity Detection) filtered out all audio.

The log shows duration=1093.4s (the file has audio) but duration_after_vad=0.0s (VAD detected zero speech).

Two settings in your _kw are wrong and must be fixed:

  • threshold: 1.0 → VAD speech probability threshold is at maximum, so only audio with 100% certainty of being speech passes.

    Almost nothing qualifies.
  • no_speech_threshold: 1.0 → also at maximum, and combined with min_speech_duration_ms=0 / min_silence_duration_ms=2000, everything is treated as non-speech.

Fix steps:

  1. Go to Menu → Tools/Options → Advanced Options → ASR Settings.
  2. Set VAD: Speech probability threshold (语音阈值) to the default 0.5 (or 0.4 if the audio is quiet).
  3. Set no speech threshold (非语音阈值) back to 0.6 (default).

    Never use 1.0.
  4. Verify VAD: min speech duration(ms) = 3000 and VAD: silence duration for split(ms) = 600 (defaults).
  5. Re-run with Clear Output checked.

If it still reports no human voice:

  • Tick 设置更多参数 → 分离人声背景声 (Separate Vocal/BGM) so noise/background doesn't mask the speech.
  • If using clone role, do NOT set min speech below 3000ms.
  • Confirm the file actually contains audible speech by playing it locally.

Note: the initial_prompt you see is your translation instruction text being passed to Whisper; it is harmless, but it is not the cause of this error.

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