29 lines
698 B
Python
29 lines
698 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)
|
|
|
|
import sys
|
|
from funasr import AutoModel
|
|
|
|
model_dir = r".\QWen\pretrained_models\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,
|
|
)
|
|
|
|
print(res)
|
|
# import pdb; pdb.set_trace()
|
|
print(res[0]['text'].split(">")[-1])
|