#8575 cannot reshape tensor of 0 elements into shape [-1, 0] because the unspecified dimension size -1 can be any value and is

cannot reshape tensor of 0 elements into shape [-1, 0] because the unspecified dimension size -1 can be any value and is ambiguous,Traceback (most recent call last):
File "videotrans\process\omnivoice_tts.py", line 75, in omnivoice_fun
File "D:\BaiduNetdiskDownload\win-pyvideotrans-v4.17\_internal\torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "omnivoice\models\omnivoice.py", line 685, in generate

full_task = self._preprocess_all(

File "omnivoice\models\omnivoice.py", line 1087, in _preprocess_all

self.create_voice_clone_prompt(

File "omnivoice\models\omnivoice.py", line 757, in create_voice_clone_prompt

ref_wav = load_audio(ref_audio, self.sampling_rate)

File "omnivoice\utils\audio.py", line 84, in load_audio

data = torchaudio.functional.resample(

File "D:\BaiduNetdiskDownload\win-pyvideotrans-v4.17\_internal\torchaudio\functional\functional.py", line 1530, in resample

resampled = _apply_s

......
ompt

ref_wav = load_audio(ref_audio, self.sampling_rate)

File "omnivoice\utils\audio.py", line 84, in load_audio

data = torchaudio.functional.resample(

File "D:\BaiduNetdiskDownload\win-pyvideotrans-v4.17\_internal\torchaudio\functional\functional.py", line 1530, in resample

resampled = _apply_sinc_resample_kernel(waveform, orig_freq, new_freq, gcd, kernel, width)

File "D:\BaiduNetdiskDownload\win-pyvideotrans-v4.17\_internal\torchaudio\functional\functional.py", line 1462, in _apply_sinc_resample_kernel

waveform = waveform.view(-1, shape[-1])

RuntimeError: cannot reshape tensor of 0 elements into shape [-1, 0] because the unspecified dimension size -1 can be any value and is ambiguous

trk=[TransCreate]: uuid='ed632917f6', proxy_str=None, cfg=[TaskCfgVTT]当前工作模式: 翻译视频 单视频模式
原始输入文件名: D:/BaiduNetdiskDownload/Videos/1-4_no_sub.mp4,
输出结果保存到文件夹: D:/BaiduNetdiskDownload/Videos/_video_out/1-4_no_sub-mp4,
临时文件夹: D:/BaiduNetdiskDownload/win-pyvideotrans-v4.17/tmp/11872/ed632917f6
已选 清理已存在
已启用CUDA加速
已选 降噪, 降噪模型:dpdfnet4.onnx
已选 识别说话人，最大说话人数量7
语音识别:阿里FunASR(内置), SenseVoiceSmall, 发音语言: 简体中文, ,
翻译渠道:DeepSeek,原始语言:简体中文,目标语言:印度尼西亚, 未选 发送完整字幕, settings.get('trans_thread')=5, settings.get('aitrans_thread')=40
配音渠道:OmniVoice(内置), 角色:clone, 配音语言:印度尼西亚, 未选 二次语音识别
音量:+0%, 语速:+0%, 已选 音频加速, 未选 视频慢速
已选 移除每条字幕配音开头和结尾静音缓冲
静音移除力度: default
字幕: 嵌入硬字幕
已选 分离人声与背景声, 分离模型为:UVR-MDX-NET-Inst_HQ_4, 已选 重新嵌入背景声, 背景音量0.8, 背景声音时长 短于 视频时长时: 拉长(降速播放),存在分离后的纯净人声文件,存在分离后的背景声音文件, precent=15, hasend=False, should_recogn=True, should_trans=True, should_dubbing=True, should_hebing=True, is_copy_video=True, video_codec_num=264, ignore_align=False, is_audio_trans=False, clone_ref='D:/BaiduNetdiskDownload/win-pyvideotrans-v4.17/tmp/11872/ed632917f6/vocal.wav', should_recogn2=False, do_diarize=True
video_duration_ms=426700