import gradio as gr
from transformers import pipeline

# Load ASR model
transcriber = pipeline(
    "automatic-speech-recognition", 
    model="openai/whisper-base"
)

# Transcription function
def transcribe_audio(audio):
    if audio is None:
        return "No audio recorded. Please record something."
    
    result = transcriber(audio)
    return result["text"]

# Create interface
interface = gr.Interface(
    fn=transcribe_audio,
    inputs=gr.Audio(sources=["microphone"], type="filepath"),
    outputs=gr.Textbox(label="Transcription"),
    title="Automatic Speech Recognition",
    description="Click the microphone icon, speak, then click stop. Your speech will be transcribed."
)

# Launch
interface.launch()