app.py

import gradio as gr
from transformers import pipeline
import time

# p = pipeline("automatic-speech-recognition", model="/Users/mkesavan/aidev/speechAI-trials/xlsr-wave2vec/wav2vec2-large-xls-r-300m-tamil-colab/checkpoint-1600")

p = pipeline("automatic-speech-recognition", model="kmknair/wav2vec2-xlsr-tamil")

def transcribe(audio, state=""):
    time.sleep(2)
    text = p(audio)["text"]
    state += text + " " 
    return state, state


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