app.py

# import gradio as gr

# gr.Interface.load("models/rohitp1/kkkh_whisper_small_distillation_att_loss_libri360_epochs_100_batch_4_concat_dataset").launch()


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

p = pipeline('automatic-speech-recognition', model='rohitp1/kkkh_whisper_small_distillation_att_loss_libri360_epochs_100_batch_4_concat_dataset')

def transcribe(audio, state=""):
    time.sleep(3)
    text = p(audio)["text"]
    state += text + " "
    return state, state



gr.Interface(
    fn=transcribe, 
    inputs=[
        gr.inputs.Audio(source="microphone", type="filepath"),
        'state'
    ],
    outputs=[
        "textbox",
        "state"
    ],
    live=False).launch()