语音识别阶段出错[Huggingface_ASR(内置)] The expanded size of the tensor (3000) must match the existing size (3529) at non-singleton dimension 1. Target sizes: [128, 3000]. Tensor sizes: [128, 3529]:Traceback (most recent call last):
File "videotrans\process\stt_pipe.py", line 61, in pipe_asr
File "D:\win-pyvideotrans-v4.16-1\_internal\transformers\pipelines\automatic_speech_recognition.py", line 247, in call
return super().__call__(inputs, **kwargs)File "D:\win-pyvideotrans-v4.16-1\_internal\transformers\pipelines\base.py", line 1257, in call
outputs = list(final_iterator)File "D:\win-pyvideotrans-v4.16-1\_internal\transformers\pipelines\pt_utils.py", line 126, in next
item = next(self.iterator)File "D:\win-pyvideotrans-v4.16-1\_internal\transformers\pipelines\pt_utils.py", line 271, in next
processed = self.infer(next(self.iterator), **self.params)File "D:\win-pyvideotrans-v4.16-1\_internal\torch\utils\data\dataloader.py", line 733, in
......
4.16-1\_internal\transformers\pipelines\base.py", line 1257, in call
outputs = list(final_iterator)File "D:\win-pyvideotrans-v4.16-1\_internal\transformers\pipelines\pt_utils.py", line 126, in next
item = next(self.iterator)File "D:\win-pyvideotrans-v4.16-1\_internal\transformers\pipelines\pt_utils.py", line 271, in next
processed = self.infer(next(self.iterator), **self.params)File "D:\win-pyvideotrans-v4.16-1\_internal\torch\utils\data\dataloader.py", line 733, in next
data = self._next_data()File "D:\win-pyvideotrans-v4.16-1\_internal\torch\utils\data\dataloader.py", line 789, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIterationFile "D:\win-pyvideotrans-v4.16-1\_internal\torch\utils\data\_utils\fetch.py", line 43, in fetch
return self.collate_fn(data)File "D:\win-pyvideotrans-v4.16-1\_internal\transformers\pipelines\base.py", line 174, in inner
padded[key] = _pad(items, key, _padding_value, padding_side)File "D:\win-pyvideotrans-v4.16-1\_internal\transformers\pipelines\base.py", line 110, in _pad
tensor[i, : len(item[key][0])] = item[key][0]RuntimeError: The expanded size of the tensor (3000) must match the existing size (3529) at non-singleton dimension 1. Target sizes: [128, 3000]. Tensor sizes: [128, 3529]
trk=[SpeechToText]: uuid='be95973261', proxy_str=None, cfg=[TaskCfgSTT]
原始输入文件名: E:/DownLoad/4/rrr/カリビアンコム叶あん 近親家族 パート２_2.mp4,
输出结果保存到文件夹: D:/win-pyvideotrans-v4.16-1/output/recogn,
临时文件夹: D:/win-pyvideotrans-v4.16-1/tmp/12812/be95973261
已启用CUDA加速
已选 降噪
已选 识别说话人，最大说话人数量不限制
语音识别:Huggingface_ASR(内置), kotoba-tech/kotoba-whisper-v2.0
发音语言:ja
已选 降噪, precent=1, hasend=False, should_recogn=True, should_trans=False, should_dubbing=False, should_hebing=False, out_format='srt', copysrt_rawvideo=False, spk_insert=True
=
system:Windows-10-10.0.26100-SP0
version:v4.16
frozen:True
language:zh_CN
root_dir:D:/win-pyvideotrans-v4.16-1