TypeError: `pad_width` must be of integral type.

[1574300748]

模型可以正常加载,使用的是您提供的large2,一到开始处理就卡在这 `==========2024-07-17_19:08:02========== ==========Process==========

redirect std output vad_filter : True -threshold : 0.5 -min_speech_duration_ms : 250 -max_speech_duration_s : inf -min_silence_duration_ms : 2000 -window_size_samples : 1024 -speech_pad_ms : 400 Transcribes options: -audio : ['E:/StudyData/python/music_to_word/video-subtitle-generator-main/video-subtitle-generator-main/test/SUWK-022.mp3'] -language : None -task : True -beam_size : 5 -best_of : 5 -patience : 1.0 -length_penalty : 1.0 -temperature : [0.0, 0.2, 0.4, 0.6, 0.8, 1.0] -compression_ratio_threshold : 1.4 -log_prob_threshold : -10.0 -no_speech_threshold : 0.9 -condition_on_previous_text : False -initial_prompt : None -prefix : None -suppress_blank : True -suppress_tokens : [-1] -without_timestamps : False -max_initial_timestamp : 1.0 -word_timestamps : False -prepend_punctuations : "'“¿([{- -append_punctuations : "'.。,，!！?？:：”)]}、 -repetition_penalty : 1.0 -no_repeat_ngram_size : 0 -prompt_reset_on_temperature : 0.5 -max_new_tokens : None -chunk_length : 30.0 -clip_mode : 0 -clip_timestamps : 0 -hallucination_silence_threshold : 0.5 -hotwords : -language_detection_threshold : None -language_detection_segments : 1 create transcribe process with 1 workers start transcribe process Traceback (most recent call last): File "E:\StudyData\python\music_to_word\faster-whisper-GUI-main\faster-whisper-GUI-main\faster_whisper_GUI\transcribe.py", line 368, in run for path, results in zip(files, results): File "D:\Sofware\miniconda3\envs\voice2srt\lib\concurrent\futures_base.py", line 608, in result_iterator yield fs.pop().result() File "D:\Sofware\miniconda3\envs\voice2srt\lib\concurrent\futures_base.py", line 445, in result return self.get_result() File "D:\Sofware\miniconda3\envs\voice2srt\lib\concurrent\futures_base.py", line 390, in get_result raise self._exception File "D:\Sofware\miniconda3\envs\voice2srt\lib\concurrent\futures\thread.py", line 52, in run result = self.fn(*self.args, **self.kwargs) File "E:\StudyData\python\music_to_word\faster-whisper-GUI-main\faster-whisper-GUI-main\faster_whisper_GUI\transcribe.py", line 230, in transcribe_file segments, info = self.model.transcribe( File "D:\Sofware\miniconda3\envs\voice2srt\lib\site-packages\faster_whisper\transcribe.py", line 357, in transcribe features = self.feature_extractor(audio, chunk_length=chunk_length) File "D:\Sofware\miniconda3\envs\voice2srt\lib\site-packages\faster_whisper\feature_extractor.py", line 155, in call waveform = np.pad(waveform, [(0, self.n_samples)]) File "D:\Sofware\miniconda3\envs\voice2srt\lib\site-packages\numpy\lib\arraypad.py", line 745, in pad raise TypeError('pad_width must be of integral type.') TypeError: pad_width must be of integral type. `

[GillianJiao]

确实有时候用v3翻译突然卡死就一直显示处理中，翻译好几次俄语都出现这种情况

[CheshireCC]

确实有时候用v3翻译突然卡死就一直显示处理中，翻译好几次俄语都出现这种情况

显存不足了

[CheshireCC]

模型可以正常加载,使用的是您提供的large2,一到开始处理就卡在这 `==========2024-07-17_19:08:02========== ==========Process==========

redirect std output vad_filter : True -threshold : 0.5 -min_speech_duration_ms : 250 -max_speech_duration_s : inf -min_silence_duration_ms : 2000 -window_size_samples : 1024 -speech_pad_ms : 400 Transcribes options: -audio : ['E:/StudyData/python/music_to_word/video-subtitle-generator-main/video-subtitle-generator-main/test/SUWK-022.mp3'] -language : None -task : True -beam_size : 5 -best_of : 5 -patience : 1.0 -length_penalty : 1.0 -temperature : [0.0, 0.2, 0.4, 0.6, 0.8, 1.0] -compression_ratio_threshold : 1.4 -log_prob_threshold : -10.0 -no_speech_threshold : 0.9 -condition_on_previous_text : False -initial_prompt : None -prefix : None -suppress_blank : True -suppress_tokens : [-1] -without_timestamps : False -max_initial_timestamp : 1.0 -word_timestamps : False -prepend_punctuations : "'“¿([{- -append_punctuations : "'.。,，!！?？:：”)]}、 -repetition_penalty : 1.0 -no_repeat_ngram_size : 0 -prompt_reset_on_temperature : 0.5 -max_new_tokens : None -chunk_length : 30.0 -clip_mode : 0 -clip_timestamps : 0 -hallucination_silence_threshold : 0.5 -hotwords : -language_detection_threshold : None -language_detection_segments : 1 create transcribe process with 1 workers start transcribe process Traceback (most recent call last): File "E:\StudyData\python\music_to_word\faster-whisper-GUI-main\faster-whisper-GUI-main\faster_whisper_GUI\transcribe.py", line 368, in run for path, results in zip(files, results): File "D:\Sofware\miniconda3\envs\voice2srt\lib\concurrent\futures_base.py", line 608, in result_iterator yield fs.pop().result() File "D:\Sofware\miniconda3\envs\voice2srt\lib\concurrent\futures_base.py", line 445, in result return self.get_result() File "D:\Sofware\miniconda3\envs\voice2srt\lib\concurrent\futures_base.py", line 390, in get_result raise self._exception File "D:\Sofware\miniconda3\envs\voice2srt\lib\concurrent\futures\thread.py", line 52, in run result = self.fn(*self.args, self.kwargs) File "E:\StudyData\python\music_to_word\faster-whisper-GUI-main\faster-whisper-GUI-main\faster_whisper_GUI\transcribe.py", line 230, in transcribe_file segments, info = self.model.transcribe( File "D:\Sofware\miniconda3\envs\voice2srt\lib\site-packages\faster_whisper\transcribe.py", line 357, in transcribe features = self.feature_extractor(audio, chunk_length=chunk_length) File "D:\Sofware\miniconda3\envs\voice2srt\lib\site-packages\faster_whisper\feature_extractor.py", line 155, in call** waveform = np.pad(waveform, [(0, self.n_samples)]) File "D:\Sofware\miniconda3\envs\voice2srt\lib\site-packages\numpy\lib\arraypad.py", line 745, in pad raise TypeError('pad_width must be of integral type.') TypeError: pad_width must be of integral type. `

源代码调试的吗？