#5286 TaskCfgVTT(uuid='2d58939cdd', name='E:/videoplayback.m4a', dirname='E:/', noextname='videoplayback', basename='videoplay

Batch size mismatch: audio=8, context=0:Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 559, in qwen3asr_fun
File "torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "E:\A4\_internal\qwen_asr\inference\qwen3_asr.py", line 345, in transcribe

raise ValueError(f"Batch size mismatch: audio={n}, context={len(ctxs)}")

ValueError: Batch size mismatch: audio=8, context=0
[Qwen-ASR(本地内置), 兼容AI/本地模型, Qwen3-TTS(本地内置)]
Traceback (most recent call last):
File "videotrans\task\only_one.py", line 47, in run
File "videotrans\task\trans_create.py", line 317, in recogn
File "videotrans\recognition\__init__.py", line 190, in run
File "videotrans\recognition\_base.py", line 94, in run
File "videotrans\recognition\_qwenasrlocal.py", line 45, in _exec
File "videotrans\configure\base.py", line 268, in _new_process
videotrans.configure.excepts.VideoTransError: Batch size mismatch: audio=8, context=0:Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 559, in qwen3asr_fun
File "torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "E:\A4\_internal\qwen_asr\inference\qwen3_asr.py", line 345, in transcribe

raise ValueError(f"Batch size mismatch: audio={n}, context={len(ctxs)}")

ValueError: Batch size mismatch: audio=8, context=0
TaskCfgVTT(uuid='2d58939cdd', name='E:/videoplayback.m4a', dirname='E:/', noextname='videoplayback', basename='videoplayback.m4a', ext='m4a', target_dir='E:/_video_out/videoplayback-m4a', cache_folder='E:/A4/tmp/34692/2d58939cdd', is_cuda=True, source_language='英语', source_language_code='en', source_sub='E:/_video_out/videoplayback-m4a/en.srt', source_wav='E:/A4/tmp/34692/2d58939cdd/en.wav', source_wav_output='E:/_video_out/videoplayback-m4a/en.m4a', target_language='简体中文', target_language_code='zh-cn', target_sub='E:/_video_out/videoplayback-m4a/zh-cn.srt', target_wav='E:/A4/tmp/34692/2d58939cdd/target.wav', target_wav_output='E:/_video_out/videoplayback-m4a/zh-cn.m4a', translate_type=8, tts_type=1, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='clone', voice_autorate=False, video_autorate=False, remove_silent_mid=False, align_sub_audio=True, detect_language='en', recogn_type=2, model_name='1.7B', shibie_audio=None, remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=0, subtitle_language=None, app_mode='biaozhun', subtitles='', targetdir_mp4='E:/_video_out/videoplayback-m4a/videoplayback.mp4', novoice_mp4='E:/A4/tmp/34692/2d58939cdd/novoice.mp4', is_separate=False, embed_bgm=True, instrument='E:/A4/tmp/34692/2d58939cdd/instrument.wav', vocal='E:/A4/tmp/34692/2d58939cdd/vocal.wav', clear_cache=False, background_music='', subtitle_type=0, only_out_mp4=False, recogn2pass=False, output_srt=0, copysrt_rawvideo=False, loop_backaudio=1, backaudio_volume=0.8)