from transformers import pipeline
import gradio as gr


pipe = pipeline(
    "automatic-speech-recognition",
    model="MohammadGholizadeh/whisper-large-v3-persian-common-voice-17",
    chunk_length_s=30,
    return_timestamps=False
)

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


iface = gr.Interface(
    fn=transcribe, 
    inputs=gr.Audio(sources=["microphone", "upload"], type="filepath"),  # Allow both sources: microphone and file upload
    outputs="text",
    title="Whisper Large V3 Persian",
    description="Realtime demo for Persian speech recognition using a fine-tuned Whisper Large model on Mozilla Common Voice.",
)

iface.launch()