from funasr import AutoModel

model = AutoModel(
    model="Whisper-large-v3",
    kwargs={"model_path": "/data/llvm/whisper/"},
    vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
    vad_kwargs={"max_single_segment_time": 30000},
    punc_model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
    # return_spk_res=True,
    word_timestamps=True,
    spk_model="iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
    # spk_model="cam++",
    hub="openai",
)

res = model.generate(
    task="transcribe",
    batch_size_s=0,
    input="/root/桌面/音频/output_30.mp3",
    # input="/root/桌面/音频/asr_example_zh.wav",
    # sentence_timestamp=True,
    is_final=True,
)

print(res)

File "/data/llvm/whisper_t.py", line 16, in <module>
    res = model.generate(
  File "/usr/local/lib/python3.10/dist-packages/funasr/auto/auto_model.py", line 224, in generate
    return self.inference_with_vad(input, input_len=input_len, **cfg)
  File "/usr/local/lib/python3.10/dist-packages/funasr/auto/auto_model.py", line 358, in inference_with_vad
    spk_res = self.inference(speech_b, input_len=None, model=self.spk_model, kwargs=kwargs, **cfg)
  File "/usr/local/lib/python3.10/dist-packages/funasr/auto/auto_model.py", line 257, in inference
    res = model.inference(**batch, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/funasr/models/bicif_paraformer/model.py", line 253, in inference
    speech, speech_lengths = extract_fbank(audio_sample_list, data_type=kwargs.get("data_type", "sound"),
  File "/usr/local/lib/python3.10/dist-packages/funasr/utils/load_utils.py", line 131, in extract_fbank
    data, data_len = frontend(data, data_len, **kwargs)