from transformers import pipeline
import gradio as gr

# Specify the task explicitly
pipe = pipeline(task="automatic-speech-recognition", model="erkhem-gantulga/whisper-medium-mn")

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

iface = gr.Interface(
    fn=transcribe,
    inputs=gr.Audio(sources=["upload", "microphone"], type="filepath"),
    outputs="text",
    title="Whisper Medium Mongolian",
    description="Realtime demo for Mongolian speech recognition using a fine-tuned Whisper medium model.",
)

iface.launch()