File size: 626 Bytes
43f775e
bee0b24
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import torch
from transformers import pipeline
import numpy as np
import gradio as gr

pipe = pipeline(
    "automatic-speech-recognition", model="openai/whisper-base"
)

def transcribe(stream, nuevo_fragmento):
    sr, y = nuevo_fragmento
    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, pipe({"sampling_rate": sr, "raw": stream})["text"]

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

demo.launch()