mirror of
https://github.com/modelscope/FunASR
synced 2025-09-15 14:48:36 +08:00
65396eeeff
* fix add_file bug (#1296) Co-authored-by: shixian.shi <shixian.shi@alibaba-inc.com> * funasr1.0 uniasr * funasr1.0 uniasr * update with main (#1305) * v1.0.3 * update clients for 2pass * update download tools --------- Co-authored-by: 雾聪 <wucong.lyb@alibaba-inc.com> * vad streaming return [beg, -1], [], [-1, end], [beg, end]] --------- Co-authored-by: shixian.shi <shixian.shi@alibaba-inc.com> Co-authored-by: 雾聪 <wucong.lyb@alibaba-inc.com>
40 lines
1.1 KiB
Python
40 lines
1.1 KiB
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
|
|
wav_file = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav"
|
|
|
|
model = AutoModel(model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch", model_revision="v2.0.4")
|
|
|
|
res = model.generate(input=wav_file)
|
|
print(res)
|
|
|
|
|
|
|
|
import soundfile
|
|
import os
|
|
|
|
wav_file = os.path.join(model.model_path, "example/vad_example.wav")
|
|
speech, sample_rate = soundfile.read(wav_file)
|
|
|
|
chunk_size = 200 # ms
|
|
chunk_stride = int(chunk_size * sample_rate / 1000)
|
|
|
|
cache = {}
|
|
|
|
total_chunk_num = int(len((speech)-1)/chunk_stride+1)
|
|
for i in range(total_chunk_num):
|
|
speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
|
|
is_final = i == total_chunk_num - 1
|
|
res = model.generate(input=speech_chunk,
|
|
cache=cache,
|
|
is_final=is_final,
|
|
chunk_size=chunk_size,
|
|
disable_pbar=True,
|
|
)
|
|
# print(res)
|
|
if len(res[0]["value"]):
|
|
print(res)
|