app.py

import transformers
from transformers import pipeline
import gradio as gr
import os 
import sys 
os.system("pip install evaluate")
os.system("pip install datasets")
from evaluate import evaluator
from datasets import load_dataset

p = pipeline("automatic-speech-recognition")

task_evaluator = evaluator("automatic-speech-recognition")
data = load_dataset("mskov/miso_test", "en", split="test[:40]")
results = task_evaluator.compute(
    model_or_pipeline="https://huggingface.co/mskov/whisper_miso",
    data=data,
    input_column="path",
    label_column="category",
    metric="wer",
)
print(results)


def transcribe(audio, state=""):
    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()