mirror of
https://github.com/modelscope/FunASR
synced 2025-09-15 14:48:36 +08:00
00d0df3a10
* resume from step * batch * batch * batch * batch * batch * batch * batch * batch * batch * batch * batch * batch * batch * batch * batch * train_loss_avg train_acc_avg * train_loss_avg train_acc_avg * train_loss_avg train_acc_avg * log step * wav is not exist * wav is not exist * decoding * decoding
28 lines
786 B
Python
28 lines
786 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
|
|
|
|
model = AutoModel(
|
|
model="/Users/zhifu/Downloads/modelscope_models/SenseVoiceModelscopeFSMN",
|
|
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/ASR/test_audio/asr_example_zh.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, beam_size=5)
|
|
print(res)
|