-
Notifications
You must be signed in to change notification settings - Fork 12
/
app.py
71 lines (58 loc) · 2.01 KB
/
app.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
# Copyright (c) 2022 Horizon Robotics. (authors: Binbin Zhang)
# 2022 Chengdong Liang ([email protected])
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import gradio as gr
import wenet
# TODO: add hotword
chs_model = wenet.load_model('chinese')
en_model = wenet.load_model('english')
def recognition(audio, lang='CN'):
if audio is None:
return "Input Error! Please enter one audio!"
# NOTE: model supports 16k sample_rate
if lang == 'CN':
ans = chs_model.transcribe(audio)
elif lang == 'EN':
ans = en_model.transcribe(audio)
else:
return "ERROR! Please select a language!"
if ans is None:
return "ERROR! No text output! Please try again!"
txt = ans['text']
return txt
# input
inputs = [
gr.inputs.Audio(source="microphone", type="filepath", label='Input audio'),
gr.Radio(['EN', 'CN'], label='Language')
]
output = gr.outputs.Textbox(label="Output Text")
text = "Speech Recognition in WeNet | 基于 WeNet 的语音识别"
# description
description = (
"Wenet Demo ! This is a speech recognition demo that supports Mandarin and English !" # noqa
)
article = (
"<p style='text-align: center'>"
"<a href='https://github.com/wenet-e2e/wenet' target='_blank'>Github: Learn more about WeNet</a>" # noqa
"</p>")
interface = gr.Interface(
fn=recognition,
inputs=inputs,
outputs=output,
title=text,
description=description,
article=article,
theme='huggingface',
)
interface.launch(enable_queue=True)