import gradio as gr
import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline

model_id = "KingNish/whisper-small-en"

pipe = pipeline(
    "automatic-speech-recognition",
    model=model_id
)

def transcribe(audio):
    text = pipe(audio)["text"]
    return text

iface = gr.Interface(
    fn=transcribe,
    inputs=gr.Audio(type="filepath"),
    outputs="text",
    title="Whisper Small Hindi",
    description="Realtime demo for Hindi speech recognition using a fine-tuned Whisper small model.",
)

iface.launch()