#7750 语音识别阶段出错[faster-whisper(本地内置)] No transcription results returned. Please check the original audio/video or model and try

125.67**6 Posted at: 1 hour ago

语音识别阶段出错[faster-whisper(本地内置)] No transcription results returned. Please check the original audio/video or model and try again.
info=TranscriptionInfo(language='en', language_probability=1, duration=234.660875, 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=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, 0.2, 0.4, 0.6, 0.8, 1.0], 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, 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
......
362, 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=0.5, neg_threshold=None, min_speech_duration_ms=0, max_speech_duration_s=inf, min_silence_duration_ms=140, speech_pad_ms=400))
cfg=TaskCfgSTT(uuid='5675ea9561', name='D:/BaiduNetdiskDownload/音乐教程/教程/官方/Audiomodern-PLAYBEAT 3.1 by Audiomodern SMART Algorithm - in_4k.mp4', dirname='D:/BaiduNetdiskDownload/音乐教程/教程/官方', noextname='Audiomodern-PLAYBEAT 3.1 by Audiomodern SMART Algorithm - in_4k', basename='Audiomodern-PLAYBEAT 3.1 by Audiomodern SMART Algorithm - in_4k.mp4', ext='mp4', target_dir='D:/BaiduNetdiskDownload/pyVideoTrans/win-pyvideotrans-v4.07/output/recogn', cache_folder='D:/BaiduNetdiskDownload/pyVideoTrans/win-pyvideotrans-v4.07/tmp/27364/5675ea9561', is_cuda=False, source_language=None, source_language_code=None, source_sub=None, source_wav=None, source_wav_output=None, target_language=None, target_language_code=None, target_sub='D:/BaiduNetdiskDownload/pyVideoTrans/win-pyvideotrans-v4.07/output/recogn/Audiomodern-PLAYBEAT 3.1 by Audiomodern SMART Algorithm - in_4k.srt', target_wav=None, target_wav_output=None, detect_language='en', recogn_type=0, model_name='large-v3-turbo', shibie_audio='D:/BaiduNetdiskDownload/pyVideoTrans/win-pyvideotrans-v4.07/tmp/27364/5675ea9561/Audiomodern-PLAYBEAT 3.1 by Audiomodern _ SMART Algorithm - in_4k-1790846129.2482877.wav', remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=0)


=
system:Windows-10-10.0.26100-SP0
version:v4.07
frozen:True
language:zh
root_dir:D:/BaiduNetdiskDownload/pyVideoTrans/win-pyvideotrans-v4.07

1 Replies

#1 DeepSeek reply at 1 hour ago

核心原因是 VAD 语音活动检测后有效语音时长为 0(duration_after_vad=0.0),即整段音频未检测到符合阈值的人类语音,因此返回空转录结果。

常见原因及解决办法:

  1. 视频本身无有效人声:该文件为音乐教程/Audiomodern 演示视频,可能全程只有背景音乐、鼓点或纯音乐,无清晰讲解人声。

    请先本地播放确认是否有人声说话。

  2. 背景音乐过大掩盖人声:主界面点击设置更多参数,勾选分离人声背景声和降噪,再重试。

  3. VAD 参数过于严格:进入 菜单 → 工具/选项 → 高级选项 → 语音识别参数:

    • 将语音阈值从默认 0.5 调低(如 0.3)
    • 将非语音阈值调低
    • 将最短语音持续(毫秒)调低(如 1000)
  4. 文件路径含特殊符号:你的路径中含有 -、空格及很长的文件名,建议将视频移动到浅层纯英文短路径(如 D:/test/1.mp4)后重试。

  5. 换模型或换渠道验证:将模型换成 large-v3,或改用 openai-whisper(内置) 重试,以判断是否为模型问题。

  6. 升级软件:当前为 v4.07,建议升级到最新版本 v4.14,新版优化了 VAD 切分算法和识别对齐。

若以上均无效,请提供视频前 10 秒的音频单独测试,或提供 logs/ 目录下最新日志底部约 30 行。

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