app.py

from transformers import pipeline
pipe = pipeline('automatic-speech-recognition', model='openai/whisper-small')

def transcribe_speech(filepath):
    output = pipe(
        filepath,
        max_new_tokens = 256,
        generate_kwargs={
            "task": "transcribe",
            "language": "english",
        },  
        chunk_length_s = 30,
        batch_size = 8,
    )
    return output["text"]

import gradio as gr

demo = gr.Blocks()

mic_transcribe = gr.Interface(
    fn = transcribe_speech,
    inputs=gr.Audio(sources = "microphone", type = "filepath"),
    outputs = 'text',
)

file_transcribe = gr.Interface(
    fn = transcribe_speech,
    inputs = gr.Audio(sources = "upload", type = "filepath"),
    outputs ='text',
)

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

demo.launch()