Warning: CAUTION: The operator 'aten::_upsample_bilinear2d_aa.out' is not currently supported on the NPU backend and will fall back to run on the CPU. 

Warning: CAUTION: The operator 'aten::_fft_c2r’ is not currently suported on the NPU backend and will fall back to run on the cpu.

CANN：8.1.RC1

Torch：2.5.1

Torch_npu：2.5.1.post1

torchaudio：2.5.1

from cosyvoice.cli.cosyvoice import CosyVoice
from cosyvoice.utils.file_utils import load_wav
import torch_npu
import torchaudio

def main():
    cosyvoice = CosyVoice("./pretrained_models/CosyVoice-300M", fp16=True)
    prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)

    for i, j in enumerate(cosyvoice.inference_zero_shot('收到好友从远方寄来的生日礼物，那份意外的惊喜与深深的祝福让我心中充满了甜蜜的快乐，笑容如花儿般绽放。', '希望你以后能够做的比我还好呦。',prompt_speech_16k, stream=False)):
        torchaudio.save('zero_shot_{}.wav'.format(i), j['tts_speech'], 22050)

if __name__ == "__main__":
    torch_npu.npu.set_compile_mode(jit_compile=False)
    torch_npu.npu.config.allow_internal_format = False
    main()