#2605 TaskCfg(cache_folder='D:/win-videotrans-v3.67-tiny/tmp/23588/speech2text', target_dir='E:/Doc/pyvideo/recogn', remove_no

语音识别阶段出错:[阿里FunASR中文(本地)] 程序内部错误：expected Tensor as element 1 in argument 0, but got str:
Traceback (most recent call last):
File "videotrans\task\job.py", line 113, in run
File "videotrans\task\_speech2text.py", line 146, in recogn
File "videotrans\recognition\__init__.py", line 227, in run
File "videotrans\recognition\_base.py", line 80, in run
File "videotrans\recognition\_funasr.py", line 60, in _exec
File "funasr\auto\auto_model.py", line 306, in generate

return self.inference_with_vad(input, input_len=input_len, **cfg)

File "funasr\auto\auto_model.py", line 383, in inference_with_vad

res = self.inference(

File "funasr\auto\auto_model.py", line 345, in inference

res = model.inference(**batch, **kwargs)

File "D:\win-videotrans-v3.67-tiny\_internal\funasr\models\fsmn_vad_streaming\model.py", line 690, in inference

audio_sample = torch.cat((cache["prev_samples"], audio_sample_list[0]))

TypeError: expected Tensor as element 1 in argument 0, but got str

TaskCfg(cache_folder='D:/win-videotrans-v3.67-tiny/tmp/23588/speech2text', target_dir='E:/Doc/pyvideo/recogn', remove_noise=False, is_separate=False, detect_language='auto', subtitle_language=None, source_language=None, target_language=None, source_language_code=None, target_language_code=None, source_sub=None, target_sub='E:/Doc/pyvideo/recogn/2.srt', source_wav=None, source_wav_output=None, target_wav=None, target_wav_output=None, subtitles=None, novoice_mp4=None, noextname='2', shibie_audio='D:/win-videotrans-v3.67-tiny/tmp/23588/speech2text/2-1768190069.2065918.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=2, model_name='paraformer-zh', split_type=0, voice_autorate=False, video_autorate=False, cuda=True, name='E:/Downloads/2.mp4', basename='2.mp4', ext='mp4', dirname='E:/Downloads', shound_del_name=None, uuid='810edf3880', remove_silent_mid=False, align_sub_audio=True, enable_diariz=False, nums_diariz=0, rephrase=0, only_out_mp4=False)