File size: 987 Bytes
6a52be4
 
b2550bd
 
a93a793
b2550bd
 
 
 
 
 
 
 
de89caf
b2550bd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import gradio as gr

from transformers import pipeline

model_id = "burraco135/whisper-tiny-en"
pipe = pipeline("automatic-speech-recognition", model=model_id)

def transcribe_speech(filepath):
    output = pipe(
        filepath,
        max_new_tokens=256,
        generate_kwargs={
            "task": "transcribe",
            "language": "english",
        },  # update with the language you've fine-tuned on
        chunk_length_s=30,
        batch_size=8,
    )
    return output["text"]

demo = gr.Blocks()

mic_transcribe = gr.Interface(
    fn=transcribe_speech,
    inputs=gr.Audio(source="microphone", type="filepath"),
    outputs=gr.outputs.Textbox(),
)

file_transcribe = gr.Interface(
    fn=transcribe_speech,
    inputs=gr.Audio(source="upload", type="filepath"),
    outputs=gr.outputs.Textbox(),
)

with demo:
    gr.TabbedInterface(
        [mic_transcribe, file_transcribe],
        ["Transcribe Microphone", "Transcribe Audio File"],
    )

demo.launch(debug=True)