File size: 522 Bytes
711a34a
0fb5565
8bea008
711a34a
a6a9161
 
 
711a34a
8bea008
 
 
 
 
 
 
 
 
 
a6a9161
8bea008
 
 
 
 
 
0fb5565
0340380
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
import gradio as gr
from transformers import pipeline
import numpy as np

model = "openai/whisper-base.en"

pipe = pipeline("automatic-speech-recognition", model=model)

def transcribe(audio):
    sr, y = audio
    
    # Convert to mono if stereo
    if y.ndim > 1:
        y = y.mean(axis=1)
        
    y = y.astype(np.float32)
    y /= np.max(np.abs(y))

    return pipe({"sampling_rate": sr, "raw": y})["text"]  

demo = gr.Interface(
    transcribe,
    gr.Audio(sources="microphone"),
    "text",
)

demo.launch()