1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
| #!/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
|
| model = AutoModel(model="/Users/zhifu/Downloads/modelscope_models/SenseVoice",
| vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
| vad_kwargs={"max_single_segment_time": 30000},
| )
|
|
| input_wav = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/SenseVoice/aed_ser/asr_bgm.wav"
|
| DecodingOptions = {
| "task": ("ASR", "AED", "SER"),
| "language": "auto",
| "fp16": True,
| "gain_event": True,
| }
|
| res = model.generate(input=input_wav, batch_size_s=0, DecodingOptions=DecodingOptions)
| print(res)
|
|
