File size: 676 Bytes
a95b4f8
db9a501
 
a95b4f8
64843fe
 
 
a95b4f8
7e193fe
 
db9a501
 
a95b4f8
7e193fe
 
 
 
 
a95b4f8
 
db9a501
7e193fe
 
 
 
db9a501
a95b4f8
819c345
 
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
import gradio as gr
from transformers import pipeline
import numpy as np

asr_model = "distil-whisper/distil-medium.en"

transcriber = pipeline("automatic-speech-recognition", model=asr_model)

def transcribe(stream, new_chunk):
    sr, y = new_chunk
    y = y.astype(np.float32)
    y /= np.max(np.abs(y))

    if stream is not None:
        stream = np.concatenate([stream, y])
    else:
        stream = y
    return stream, transcriber({"sampling_rate": sr, "raw": stream})["text"]


demo = gr.Interface(
    transcribe,
    ["state", gr.Audio(sources=["microphone"], streaming=True)],
    ["state", "text"],
    live=True,
)

if __name__ == "__main__":
    demo.launch()