File size: 466 Bytes
a95b4f8
 
 
 
c0fb8f9
a95b4f8
cb9c21a
 
a95b4f8
 
 
cb9c21a
a95b4f8
 
 
86349f0
 
 
a95b4f8
 
86349f0
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
import gradio as gr
from transformers import pipeline
import numpy as np

transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base.en")

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

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


demo = gr.Interface(
    fn=transcribe,
    inputs=gr.Audio(sources="upload"),
    outputs=gr.outputs.Textbox(),
)

demo.launch(debug=True)