app.py

import os
import json
import gradio as gr
import wave
import pydub
import vosk

# Path to Vosk model
model_path = "models/vosk-model-small-en-us-0.15"

if not os.path.exists(model_path):
    raise FileNotFoundError(f"Model not found at {model_path}")

# Initialize the Vosk model
model = vosk.Model(model_path)

def transcribe(audio):
    rec = vosk.KaldiRecognizer(model, 16000)
    rec.AcceptWaveform(audio)
    result = rec.Result()
    text = json.loads(result).get('text', '')
    return text

iface = gr.Interface(fn=transcribe, 
                     inputs=gr.inputs.Audio(source="microphone", type="filepath"), 
                     outputs="text",
                     live=True)

if __name__ == "__main__":
    iface.launch()