#6993 语音识别阶段出错[阿里FunASR(本地内置)] CUDA out of memory. Tried to allocate 9.78 GiB. GPU 0 has a total capacity of 31.86 GiB of whic

语音识别阶段出错[阿里FunASR(本地内置)] CUDA out of memory. Tried to allocate 9.78 GiB. GPU 0 has a total capacity of 31.86 GiB of which 7.40 GiB is free. Of the allocated memory 23.38 GiB is allocated by PyTorch, and 186.63 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_funasr.py", line 76, 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:\BaiduNetdiskDownload/pyVideoTrans/win-pyvideotrans-v4.07/videotrans/codes\model.py", line 610, in inference

return self.inference_llm(

File "D:\BaiduNetdiskDownload/pyVideoTrans/win-pyvide
......
rans\win-pyvideotrans-v4.07\_internal\funasr\models\transformer\attention.py", line 90, in forward_attention

attn = torch.softmax(scores, dim=-1).masked_fill(

torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 9.78 GiB. GPU 0 has a total capacity of 31.86 GiB of which 7.40 GiB is free. Of the allocated memory 23.38 GiB is allocated by PyTorch, and 186.63 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=TaskCfgSTT(uuid='74ee6fa600', name='D:/BaiduNetdiskDownload/配乐插件教程/The Score/05.SONUSCORE-THE SCORE Preset Playthrough_1080p.mp4', dirname='D:/BaiduNetdiskDownload/配乐插件教程/The Score', noextname='05.SONUSCORE-THE SCORE Preset Playthrough_1080p', basename='05.SONUSCORE-THE SCORE Preset Playthrough_1080p.mp4', ext='mp4', target_dir='D:/BaiduNetdiskDownload/pyVideoTrans/win-pyvideotrans-v4.07/output/recogn', cache_folder='D:/BaiduNetdiskDownload/pyVideoTrans/win-pyvideotrans-v4.07/tmp/19288/74ee6fa600', is_cuda=True, source_language=None, source_language_code=None, source_sub=None, source_wav=None, source_wav_output=None, target_language=None, target_language_code=None, target_sub='D:/BaiduNetdiskDownload/pyVideoTrans/win-pyvideotrans-v4.07/output/recogn/05.SONUSCORE-THE SCORE Preset Playthrough_1080p.srt', target_wav=None, target_wav_output=None, detect_language='en', recogn_type=3, model_name='Fun-ASR-Nano-2512', shibie_audio='D:/BaiduNetdiskDownload/pyVideoTrans/win-pyvideotrans-v4.07/tmp/19288/74ee6fa600/05.SONUSCORE-THE SCORE _ Preset Playthrough_1080p-1788193144.456531.wav', remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=0)