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

pipe2 = pipeline("automatic-speech-recognition", model="ai4bharat/indicwav2vec-hindi")

def resample_to_16k(audio, orig_sr):
    y_resampled = librosa.resample(y=audio, orig_sr=orig_sr, target_sr=16000)
    return y_resampled

def transcribe(audio):
    sr,y = audio
    y = y.astype(np.float32)
    y/= np.max(np.abs(y))
    y_resampled = resample_to_16k(y,sr)
    
    trans = pipe2(y_resampled)
    
    return trans["text"]

demo = gr.Interface(
            transcribe,
            inputs="microphone",
            outputs="text",
            examples=["./Samples/Hindi_1.mp3","./Samples/Hindi_2.mp3","./Samples/Hindi_3.mp3","./Samples/Hindi_4.mp3","./Samples/Hindi_5.mp3"])
demo.launch()