import gradio as gr
from transformers import pipeline
import numpy as np

transcriber_hindi = pipeline("automatic-speech-recognition", model="ai4bharat/indicwav2vec-hindi")
transcriber_bang = pipeline("automatic-speech-recognition", model="ai4bharat/indicwav2vec_v1_bengali")
transcriber_odia = pipeline("automatic-speech-recognition", model="ai4bharat/indicwav2vec-odia")


def transcribe(audio,lang = "hindi"):
    
        
    sr, y = audio
    y = y.astype(np.float32)
    y /= np.max(np.abs(y))
    if lang  == "hindi":
        return transcriber_hindi({"sampling_rate": sr, "raw": y})["text"]
    if lang  == "bangali":
        return transcriber_bang({"sampling_rate": sr, "raw": y})["text"]
    if lang  == "odia":
        return transcriber_odia({"sampling_rate": sr, "raw": y})["text"]    


demo = gr.Interface(fn=transcribe, inputs = [gr.Audio(source="microphone"), gr.Radio(["hindi","bangali","odia"])] , outputs = "text")

demo.launch()