from funasr import AutoModel
from funasr.utils.postprocess_utils import rich_transcription_postprocess

model = AutoModel(model="./pretrained_models/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
                  disable_update=True,
                  vad_model="./pretrained_models/speech_fsmn_vad_zh-cn-16k-common-pytorch",
                  vad_kwargs={"max_single_segment_time": 60000},
                  )
def generate_asr(speech_url, hotword):

    res = model.generate(input=speech_url,
                         batch_size_s=300,
                         batch_size_threshold_s=60,
                         hotword=hotword
                         )
    
    res = rich_transcription_postprocess(res[0]["text"])

    return res

if __name__ == "__main__":
    res = generate_asr("https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav")
    print(res)