#4848 TaskCfgVTT(uuid='f35f2aa578', name='C:/Users/JT/Desktop/7569888974190234930.mp4', dirname='C:/Users/JT/Desktop', noextna

240e:33d* Posted at: 3 hours ago

No transcription results returned. Please check the original audio/video or model and try again.
Traceback (most recent call last):
File "videotrans\task\only_one.py", line 47, in run
File "videotrans\task\trans_create.py", line 320, in recogn
File "videotrans\recognition\__init__.py", line 190, in run
File "videotrans\recognition\_base.py", line 93, in run
File "videotrans\recognition\_whisper.py", line 35, in _exec
File "videotrans\recognition\_whisper.py", line 108, in _faster
File "videotrans\configure\base.py", line 252, in _new_process
videotrans.configure.excepts.VideoTransError: No transcription results returned. Please check the original audio/video or model and try again.
TaskCfgVTT(uuid='f35f2aa578', name='C:/Users/JT/Desktop/7569888974190234930.mp4', dirname='C:/Users/JT/Desktop', noextname='7569888974190234930', basename='7569888974190234930.mp4', ext='mp4', target_dir='C:/Users/JT/Desktop/六合/7569888974190234930-mp4', cache_folder='D:/BaiduNetdiskDownload/tmp/2128/f35f2aa578', is_cuda=False, source_language='简体中文', source_language_code='zh-cn', source_sub='C:/Users/JT/Desktop/六合/7569888974190234930-mp4/zh-cn.srt', source_wav='D:/BaiduNetdiskDownload/tmp/2128/f35f2aa578/zh-cn.wav', source_wav_output='C:/Users/JT/Desktop/六合/7569888974190234930-mp4/zh-cn.m4a', target_language='英语', target_language_code='en', target_sub='C:/Users/JT/Desktop/六合/7569888974190234930-mp4/en.srt', target_wav='D:/BaiduNetdiskDownload/tmp/2128/f35f2aa578/target.wav', target_wav_output='C:/Users/JT/Desktop/六合/7569888974190234930-mp4/en.m4a', translate_type=0, tts_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='No', voice_autorate=True, video_autorate=False, remove_silent_mid=False, align_sub_audio=True, detect_language='zh-cn', recogn_type=0, model_name='large-v3-turbo', shibie_audio=None, remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False, subtitle_language=None, app_mode='biaozhun', subtitles='', targetdir_mp4='C:/Users/JT/Desktop/六合/7569888974190234930-mp4/7569888974190234930.mp4', novoice_mp4='D:/BaiduNetdiskDownload/tmp/2128/f35f2aa578/novoice.mp4', is_separate=False, embed_bgm=True, instrument=None, vocal='D:/BaiduNetdiskDownload/tmp/2128/f35f2aa578/vocal.wav', clear_cache=True, background_music='', subtitle_type=1, only_out_mp4=False, recogn2pass=False, output_srt=0, copysrt_rawvideo=False, loop_backaudio=1, backaudio_volume=0.8)


=
system:Windows-10-10.0.19045-SP0
version:v4.00
frozen:True
language:zh
root_dir:D:/BaiduNetdiskDownload

1 Replies

语音识别模型 large-v3-turbo 体积很大,在 CPU 模式下需要大量内存(通常建议至少 16GB 以上)。报错“未返回转录结果”,最可能的原因是 CPU 内存不足 导致模型加载失败或中途崩溃,其次可能是 视频路径包含中文(如“桌面”“六合”)或模型文件未正确下载。


解决方案(按优先级尝试)

  1. 降低模型大小
    在主界面将模型从 large-v3-turbo 改为 basesmall,这些模型对内存要求低得多,确认是否恢复正常。
  2. 简化文件路径
    将视频文件移动到纯英文路径(如 D:\test.mp4),且文件名使用英文字母和数字(如 demo.mp4),避免使用中文、空格或特殊符号。
  3. 检查模型是否完整下载
    进入软件安装目录下的 models/ 文件夹,查看是否存在 models--Systran--faster-whisper-large-v3-turbo 文件夹,且内部文件完整(约 6GB)。若缺失或损坏,删除该文件夹,重新运行时会自动下载。
  4. 开启降噪
    勾选主界面右上角的 降噪 选项,可滤除背景噪音从而提高识别成功率。
  5. 若不着急,考虑升级硬件或使用 GPU
    安装 CUDA 12.8 + cuDNN 9.x 并勾选 CUDA加速,可大幅降低内存压力。具体教程:Windows 安装 CUDA
  6. 查看临时文件
    检查日志中 D:/BaiduNetdiskDownload/tmp/2128/f35f2aa578/zh-cn.wav 是否已生成且大小正常(非 0KB),若未生成或为 0KB,说明音频提取阶段已失败,需检查 ffmpeg 及视频格式(尝试将视频重编码为 H.264 MP4)。

请查阅相关文档:

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