当mp3时长超过3755秒时，就会报错：torch.OutOfMemoryError: CUDA out of memory.

[libingbingd]

在调用代码时，当mp3时长超过3755秒时，就会报错：torch.OutOfMemoryError: CUDA out of memory.

代码如下： def load_model_to_asr(local_path): model = AutoModel( model=model_dir, vad_model=vad_model, punc_model=punc_model, spk_model=spk_model, vad_kwargs={"max_single_segment_time": 30000}, device="cuda:0", )

# en
res = model.generate(
    #input=f"{model.model_path}/example/en.mp3",
    input=local_path,
    cache={},
    language="auto",  # "zn", "en", "yue", "ja", "ko", "nospeech"
    use_itn=True,
    batch_size_s=6000,
    merge_vad=True,  #
    merge_length_s=1500,
)

请问大佬们如何解决，或者如何使用多GPu；求解答