app.py

import gradio as gr
from transformers import pipeline
import numpy as np
#from google.cloud import speech_v1
#from google.protobuf import timestamp_pb2

transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base.en")

def transcribe(stream, audio_bytes):
    """Transcribe audio bytes to text using Google Cloud Speech to Text."""

    sr, y = audio_bytes
    y = y.astype(np.float32)
    y /= np.max(np.abs(y))
    if stream is not None:
        stream = np.concatenate([stream, y])
    else:
        stream = y
    return stream, transcriber({"sampling_rate": sr, "raw": stream})["text"]


demo = gr.Interface(
    transcribe,
    ["state", gr.Audio(sources=["microphone"], streaming=False)],
    ["state", "text"],
    live=True,
)

demo.launch()