#7388 语音识别阶段出错[Nemotron-3.5-asr-0.6b(内置)] Sequence Length: 7197 has to be less or equal than config.max_position_embeddings 50

语音识别阶段出错[Nemotron-3.5-asr-0.6b(内置)] Sequence Length: 7197 has to be less or equal than config.max_position_embeddings 5000.:Traceback (most recent call last):
File "videotrans\process\stt_nemotron.py", line 46, in nemotron_asr
File "D:\软件\视频相关\win-pyvideotrans-v4.12-0913\_internal\transformers\models\nemotron3_5_asr\generation_nemotron3_5_asr.py", line 35, in generate

return super().generate(inputs=inputs, generation_config=generation_config, **kwargs)

File "D:\软件\视频相关\win-pyvideotrans-v4.12-0913\_internal\transformers\models\nemotron_asr_streaming\generation_nemotron_asr_streaming.py", line 228, in generate

outputs = super().generate(inputs=inputs, generation_config=generation_config, **kwargs)

File "D:\软件\视频相关\win-pyvideotrans-v4.12-0913\_internal\transformers\models\parakeet\generation_parakeet.py", line 256, in generate

outputs = super().generate(inputs=inputs, generation_config=generation_config, **kwargs)

File "D:\软件\视频相关\win-pyvideotrans-v4.12-0913\
......
件\视频相关\win-pyvideotrans-v4.12-0913\_internal\transformers\utils\generic.py", line 911, in wrapper

output = func(self, *args, **kwargs)

File "D:\软件\视频相关\win-pyvideotrans-v4.12-0913\_internal\transformers\models\nemotron_asr_streaming\modeling_nemotron_asr_streaming.py", line 1007, in forward

position_embeddings = self.encode_positions(inputs_embeds, cached_frames=cached_frames)

File "D:\软件\视频相关\win-pyvideotrans-v4.12-0913\_internal\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl

return self._call_impl(*args, **kwargs)

File "D:\软件\视频相关\win-pyvideotrans-v4.12-0913\_internal\torch\nn\modules\module.py", line 1762, in _call_impl

return forward_call(*args, **kwargs)

File "D:\软件\视频相关\win-pyvideotrans-v4.12-0913\_internal\torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "D:\软件\视频相关\win-pyvideotrans-v4.12-0913\_internal\transformers\models\nemotron_asr_streaming\modeling_nemotron_asr_streaming.py", line 376, in forward

raise ValueError(

ValueError: Sequence Length: 7197 has to be less or equal than config.max_position_embeddings 5000.

self.cfg=[TaskCfgVTT]当前工作模式: 转录并翻译字幕
原始输入文件名: J:/1.最新下载/人妖和女/已下载/nvh-034/nvh-034______________.mp4,
输出结果保存到文件夹: J:/1.最新下载/人妖和女/已下载/nvh-034/_video_out/nvh-034______________-mp4,
临时文件夹: D:/软件/视频相关/win-pyvideotrans-v4.12-0913/tmp/12492/eb81d0383d
已选 清理已存在
已启用CUDA加速
未选 降噪
语音识别:Nemotron-3.5-asr-0.6b(内置), , 发音语言: 简体中文, 断句方式:默认断句
未选 目标语言，不翻译字幕
输出字幕格式: 单字幕