app.py

import gradio as gr
from faster_whisper import WhisperModel

# Load tiny model optimized for CPU
model_size = "tiny"
device = "cpu"
compute_type = "int8"
model = WhisperModel(model_size, device=device, compute_type=compute_type)

def transcribe(audio):
    if audio is None:
        return "No audio detected"
    segments, _ = model.transcribe(audio, beam_size=5)
    return "".join([segment.text for segment in segments])

# Allow both microphone and file upload
gr.Interface(
    title='Fast Whisper Speech Recognition',
    description='CPU-optimized speech-to-text using Whisper tiny model',
    fn=transcribe,
    inputs=gr.Audio(sources=["microphone", "upload"], type="filepath"),
    outputs="textbox"
).launch()