Audio features and audio tokens do not match, tokens: 756, features: 756:Traceback (most recent call last):
File "videotrans\process\stt_qwen.py", line 83, in qwen3asr_fun
File "F:\Program Files (x86)\pyvideotrans\_internal\torch\utils\_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)File "F:\Program Files (x86)\pyvideotrans\_internal\transformers\generation\utils.py", line 2645, in generate
result = decoding_method(File "F:\Program Files (x86)\pyvideotrans\_internal\transformers\generation\utils.py", line 2845, in _sample
outputs = self._prefill(File "F:\Program Files (x86)\pyvideotrans\_internal\transformers\generation\utils.py", line 3896, in _prefill
return self(**model_inputs, return_dict=True)File "F:\Program Files (x86)\pyvideotrans\_internal\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)File "F:\Program Files (x86)\pyvideotrans\_internal\torch\nn\m
......
dule.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)File "F:\Program Files (x86)\pyvideotrans\_internal\transformers\utils\generic.py", line 911, in wrapper
output = func(self, *args, **kwargs)File "F:\Program Files (x86)\pyvideotrans\_internal\transformers\models\qwen3_asr\modeling_qwen3_asr.py", line 552, in forward
special_audio_mask = self.get_placeholder_mask(File "F:\Program Files (x86)\pyvideotrans\_internal\transformers\models\qwen3_asr\modeling_qwen3_asr.py", line 520, in get_placeholder_mask
torch_compilable_check(File "F:\Program Files (x86)\pyvideotrans\_internal\transformers\utils\import_utils.py", line 1633, in torch_compilable_check
torch._check_with(error_type, cond, msg_callable)File "F:\Program Files (x86)\pyvideotrans\_internal\torch\__init__.py", line 1642, in _check_with
raise error_type(message_evaluated)ValueError: Audio features and audio tokens do not match, tokens: 756, features: 756
trk=[TransCreate]: uuid='8a00929af7', 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:/Downloads/Video/Real-757-pilot-SnapYT.App.mp4,
输出结果保存到文件夹: D:/Downloads/Video/Real-757-pilot-SnapYT.App-mp4,
临时文件夹: F:/Program Files (x86)/pyvideotrans/tmp/14008/8a00929af7
未选 清理已存在
已启用CUDA加速
语音识别:Qwen-ASR(内置), 0.6B, 发音语言: 英语, LLM纠错,
翻译渠道:DeepSeek,原始语言:英语,目标语言:简体中文, 已选 发送完整字幕, settings.get('trans_thread')=5, settings.get('aitrans_thread')=40
配音渠道:Edge-TTS(免费), 角色:Yunjian(Male/CN), 配音语言:简体中文
已选 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: 不嵌入字幕 , precent=4, 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='', should_recogn2=True, do_diarize=True
video_duration_ms=4712650
=
system:Windows-10-10.0.26300-SP0
version:v4.17
frozen:True
language:zh_CN
root_dir:F:/Program Files (x86)/pyvideotrans