#!/usr/bin/env python3
# -*- encoding: utf-8 -*-
# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
#  MIT License  (https://opensource.org/licenses/MIT)

from model import SenseVoiceSmall
from funasr.utils.postprocess_utils import rich_transcription_postprocess


model_dir = "iic/SenseVoiceSmall"
m, kwargs = SenseVoiceSmall.from_pretrained(model=model_dir, device="cuda:0")


res = m.inference(
    data_in=f"{kwargs['model_path']}/example/en.mp3",
    language="auto", # "zn", "en", "yue", "ja", "ko", "nospeech"
    use_itn=False,
    **kwargs,
)

text = rich_transcription_postprocess(res[0][0]["text"])
print(text)