from transformers import pipeline
import gradio as gr
import os
import torch



device = torch.device("cuda" if torch.cuda.is_available() else "cpu")


auth_token = os.environ.get("hf_token")
if not auth_token:
    raise ValueError("Hugging Face token is missing! Add it as a secret.")
    
pipe = pipeline(model="fahadqazi/whisper-small-sindhi", device=device, token=auth_token)  # change to "your-username/the-name-you-picked"

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

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

iface.launch()