#3063 TaskCfg(cache_folder='F:/EDITVIDEO/win-pyvideotrans-v3.91/tmp/4368/2e0d4431f9', target_dir='f:/editvideo/win-pyvideotran

117.1* Posted at: 13 hours ago 👁8

ASR Error [faster-whisper (Local)] Chinese Haircut (7).mp4No subs recognized. Check Audio/Lang.
Traceback (most recent call last):
File "videotrans\task\job.py", line 113, in run
File "videotrans\task\_speech2text.py", line 161, in recogn
RuntimeError: Chinese Haircut (7).mp4No subs recognized. Check Audio/Lang.

TaskCfg(cache_folder='F:/EDITVIDEO/win-pyvideotrans-v3.91/tmp/4368/2e0d4431f9', target_dir='f:/editvideo/win-pyvideotrans-v3.91/output/recogn', remove_noise=False, is_separate=False, detect_language='zh-cn', subtitle_language=None, source_language=None, target_language=None, source_language_code=None, target_language_code=None, source_sub=None, target_sub='f:/editvideo/win-pyvideotrans-v3.91/output/recogn/Chinese Haircut (7).srt', source_wav=None, source_wav_output=None, target_wav=None, target_wav_output=None, subtitles=None, novoice_mp4=None, noextname='Chinese Haircut (7)', shibie_audio='F:/EDITVIDEO/win-pyvideotrans-v3.91/tmp/4368/2e0d4431f9/Chinese Haircut (7)-1770120036.7625508.wav', targetdir_mp4=None, instrument=None, vocal=None, back_audio=None, background_music=None, app_mode='biaozhun', subtitle_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role=None, copysrt_rawvideo=False, clear_cache=False, translate_type=None, tts_type=None, recogn_type=0, model_name='large-v3', split_type=0, voice_autorate=False, video_autorate=False, cuda=True, name='F:/video/china haircut/Chinese Haircut (7).mp4', basename='Chinese Haircut (7).mp4', ext='mp4', dirname='F:/video/china haircut', shound_del_name=None, uuid='2e0d4431f9', remove_silent_mid=False, align_sub_audio=True, enable_diariz=False, nums_diariz=0, rephrase=0, only_out_mp4=False)

=
system:Windows-10-10.0.26100-SP0
version:v3.91
frozen:True
language:en
root_dir:F:/EDITVIDEO/win-pyvideotrans-v3.91

1 Replies

Floor #1 DeepSeek Posted at 13 hours ago

The error "No subs recognized. Check Audio/Lang." indicates that the faster-whisper model failed to detect any speech in the audio file. This is typically caused by incorrect language settings, audio issues, or model download problems.

  1. Check and Set the Source Language: Do not rely on "Auto" detection. In the "Source Language" dropdown menu, explicitly select the correct language for your video (e.g., zh-cn for Mandarin Chinese).
  2. Verify the Audio Track: Ensure your video file contains a valid audio track. You can use the "Separate" tool in the software to extract the audio and check if it's audible.

  3. Adjust Recognition Parameters: In "Menu -> Settings -> Advanced Options -> Speech Recognition Parameters":

    • Try lowering the "Speech Threshold (VAD)" value (e.g., to 0.3) to make the model more sensitive to speech.
    • Ensure "CUDA" is enabled if you have an NVIDIA GPU.

  4. Check Model Files: The error might occur if the large-v3 model failed to download. Navigate to the models/ folder in your software directory and check for a folder named models--Systran--faster-whisper-large-v3. If it's missing or incomplete, you need to manually download the model.

    • Manual Download: Download the model from a HuggingFace mirror (e.g., https://hf-mirror.com/Systran/faster-whisper-large-v3). Place the entire downloaded folder into your models/ directory, ensuring the folder name is exactly models--Systran--faster-whisper-large-v3.
  5. Try a Different Model: As a test, switch to a smaller model like medium or small in the recognition settings to see if it works.

Please refer to the relevant documentation:

Post Your Reply
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.

Related resource