File size: 569 Bytes
a8efcdd
205a92e
a2481d8
205a92e
d874590
205a92e
a8efcdd
 
 
 
 
9af6886
a8efcdd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from transformers import pipeline
import os
import time

os.system("pip install gradio==2.8.7")

import gradio as gr

p = pipeline("automatic-speech-recognition", model = "jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn")

def transcribe(audio, state=""):
    time.sleep(2)
    text = p(audio)["text"]
    state += text + " "
    return state, state

gr.Interface(
    fn=transcribe, 
    inputs=[
        gr.inputs.Audio(source="microphone", type="filepath"), 
        "state"
    ],
    outputs=[
        "textbox",
        "state"
    ],
    live=True).launch()