语音识别阶段出错[阿里FunASR(本地)(本地内置)] CUDA out of memory. Tried to allocate 4.11 GiB. GPU 0 has a total capacity of 7.96 GiB of which 0 bytes is free. Of the allocated memory 11.89 GiB is allocated by PyTorch, and 83.73 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables):Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 636, in funasr_mlt
File "funasr\auto\auto_model.py", line 324, in generate
return self.inference(File "funasr\auto\auto_model.py", line 381, in inference
res = model.inference(**batch, **kwargs)File "D:\Tool/win-pyvideotrans-v4.03-0622/videotrans/codes\model.py", line 610, in inference
return self.inference_llm(File "D:\Tool/win-pyvideotrans-v4.03-0622/videotrans/codes\model.py", line 628
......
line 90, in run
File "videotrans\recognition\_funasr.py", line 61, in _exec
File "videotrans\configure\base.py", line 272, in _new_process
videotrans.configure.excepts.VideoTransError: CUDA out of memory. Tried to allocate 4.11 GiB. GPU 0 has a total capacity of 7.96 GiB of which 0 bytes is free. Of the allocated memory 11.89 GiB is allocated by PyTorch, and 83.73 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables):Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 636, in funasr_mlt
File "funasr\auto\auto_model.py", line 324, in generate
return self.inference(File "funasr\auto\auto_model.py", line 381, in inference
res = model.inference(**batch, **kwargs)File "D:\Tool/win-pyvideotrans-v4.03-0622/videotrans/codes\model.py", line 610, in inference
return self.inference_llm(File "D:\Tool/win-pyvideotrans-v4.03-0622/videotrans/codes\model.py", line 628, in inference_llm
inputs_embeds, contents, batch, source_ids, meta_data = self.inference_prepare(File "D:\Tool/win-pyvideotrans-v4.03-0622/videotrans/codes\model.py", line 493, in inference_prepare
encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)File "D:\Tool/win-pyvideotrans-v4.03-0622/videotrans/codes\model.py", line 272, in encode
encoder_out, encoder_out_lens = self.audio_encoder(speech, speech_lengths)File "torch\nn\modules\module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)File "torch\nn\modules\module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)File "D:\Tool\win-pyvideotrans-v4.03-0622\_internal\funasr\models\sense_voice\model.py", line 568, in forward
encoder_outs = encoder_layer(xs_pad, masks)File "torch\nn\modules\module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)File "torch\nn\modules\module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)File "D:\Tool\win-pyvideotrans-v4.03-0622\_internal\funasr\models\sense_voice\model.py", line 388, in forward
self.self_attn(File "torch\nn\modules\module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)File "torch\nn\modules\module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)File "D:\Tool\win-pyvideotrans-v4.03-0622\_internal\funasr\models\sense_voice\model.py", line 232, in forward
att_outs = self.forward_attention(v_h, scores, mask, mask_att_chunk_encoder)File "D:\Tool\win-pyvideotrans-v4.03-0622\_internal\funasr\models\sense_voice\model.py", line 200, in forward_attention
attn = torch.softmax(scores, dim=-1).masked_fill(torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 4.11 GiB. GPU 0 has a total capacity of 7.96 GiB of which 0 bytes is free. Of the allocated memory 11.89 GiB is allocated by PyTorch, and 83.73 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
cfg=[TaskCfgVTT]当前工作模式: 转录并翻译字幕
原始输入文件名: G:/七天(1)/2020.11.11黄先生代班，风骚兔女郎，小作精黑丝诱惑淫荡尤物，激情啪啪淫声浪语撸管必备.mp4,
输出结果保存到文件夹: G:/七天(1)/_video_out/2020.11.11黄先生代班，风骚兔女郎，小作精黑丝诱惑淫荡尤物，激情啪啪淫声浪语撸管必备-mp4,
临时文件夹: D:/Tool/win-pyvideotrans-v4.03-0622/tmp/16364/9e053a4f73
已选 清理已存在
已选 启用CUDA加速
未选 降噪
语音识别:阿里FunASR(本地)(本地内置), model_name: Fun-ASR-Nano-2512, 发音语言: 简体中文, 断句方式:默认断句
发音语言和目标语言相同，不翻译字幕
已选 将生成的字幕复制到视频目录下
输出字幕格式: 单字幕
代理地址:
=
system:Windows-10-10.0.26200-SP0
version:v4.03
frozen:True
language:zh
root_dir:D:/Tool/win-pyvideotrans-v4.03-0622