SenseVoice/demo_funasr.py
2024-07-10 11:36:55 +08:00

29 lines
728 B
Python

#!/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 funasr import AutoModel
from funasr.utils.postprocess_utils import rich_transcription_postprocess
model_dir = "iic/SenseVoiceSmall"
input_file = (
"https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav"
)
model = AutoModel(
model=model_dir,
trust_remote_code=True,
)
res = model.generate(
input=input_file,
cache={},
language="auto", # "zn", "en", "yue", "ja", "ko", "nospeech"
use_itn=False,
)
text = rich_transcription_postprocess(res[0]["text"])
print(text)