File size: 1,186 Bytes
437c3df
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15f1150
437c3df
 
 
 
 
 
15f1150
437c3df
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
import gradio as gr
import numpy as np
from transformers import pipeline
import torch

device = "cuda:0" if torch.cuda.is_available() else "cpu"

transcriber = pipeline("automatic-speech-recognition", model="mahimairaja/whisper-base-tamil", \
                        chunk_length_s=15, device=device)
transcriber.model.config.forced_decoder_ids = transcriber.tokenizer.get_decoder_prompt_ids(language="ta", task="transcribe")

def transcribe(audio):
    return transcriber(audio)["text"]

TITLE = "ASR for ALL - Democratizing Tamil"

demo = gr.Blocks()

mic_transcribe = gr.Interface(
    fn=transcribe,
    inputs=gr.Audio(sources="microphone", type="filepath"),
    outputs="text",
    title=TITLE,
)

file_transcribe = gr.Interface(
    fn=transcribe,
    inputs=gr.Audio(sources="upload", type="filepath"),
    outputs="text",
    examples=[
        "assets/tamil-audio-01.mp3",
        "assets/tamil-audio-02.mp3",
        "assets/tamil-audio-03.mp3",
        "assets/tamil-audio-04.mp3",
    ],
    title=TITLE,
)


with demo:
    gr.TabbedInterface(
        [mic_transcribe, file_transcribe],
        ["Real Time Transcription", "Audio File", ]
        )

demo.launch(share=True)