app.py

import gradio as gr
from transformers import pipeline

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

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

demo = gr.Blocks()

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

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

demo.launch(debug=True)