#6849 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 74, in omnivoice_fun
File "E:\A4.9\_internal\torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "omnivoice\models\omnivoice.py", line 567, in generate

voice_clone_prompt=voice_clone_prompt,

File "omnivoice\models\omnivoice.py", line 959, in _preprocess_all
File "omnivoice\models\omnivoice.py", line 702, in create_voice_clone_prompt

ref_text = add_punctuation(ref_text)

File "E:\A4.9\_internal\transformers\models\higgs_audio_v2_tokenizer\modeling_higgs_audio_v2_tokenizer.py", line 543, in encode

e_semantic_input = self._extract_semantic_features(input_values).detach()

File "E:\A4.9\_internal\transformers\models\higgs_audio_v2_tokenizer\modeling_higgs_audio_v2_tokenizer.py", line 491, in _extract
......
cified dimension size -1 can be any value and is ambiguous,Traceback (most recent call last):
File "videotrans\process\omnivoice_tts.py", line 74, in omnivoice_fun
File "E:\A4.9\_internal\torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "omnivoice\models\omnivoice.py", line 567, in generate

voice_clone_prompt=voice_clone_prompt,

File "omnivoice\models\omnivoice.py", line 959, in _preprocess_all
File "omnivoice\models\omnivoice.py", line 702, in create_voice_clone_prompt

ref_text = add_punctuation(ref_text)

File "E:\A4.9\_internal\transformers\models\higgs_audio_v2_tokenizer\modeling_higgs_audio_v2_tokenizer.py", line 543, in encode

e_semantic_input = self._extract_semantic_features(input_values).detach()

File "E:\A4.9\_internal\transformers\models\higgs_audio_v2_tokenizer\modeling_higgs_audio_v2_tokenizer.py", line 491, in _extract_semantic_features

input_values = torchaudio.functional.resample(

File "E:\A4.9\_internal\torchaudio\functional\functional.py", line 1530, in resample

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

File "E:\A4.9\_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

cfg=[TaskCfgVTT]当前工作模式: 翻译视频 单视频模式
原始输入文件名: E:/videoplayback_(Vocals).wav,
输出结果保存到文件夹: E:/_video_out/videoplayback_(Vocals)-wav,
临时文件夹: E:/A4.9/tmp/38800/2582544d82
未选 清理已存在
已启用CUDA加速
未选 降噪
语音识别:Qwen-ASR(内置), 1.7B, 发音语言: 英语, 断句方式:默认断句
翻译渠道:兼容AI/本地模型,原始语言:英语,目标语言:简体中文, 已选 发送完整字幕
配音渠道:OmniVoice(内置), 角色:clone, 配音语言:简体中文, 未选 二次语音识别
音量:+0%, 语速:+0%, 未选 音频加速, 未选 视频慢速
未选 移除字幕间空隙, 已选 强制对齐字幕和声音
字幕: 嵌入软字幕