File size: 1,063 Bytes
a95b4f8 db9a501 a95b4f8 64843fe 1f6c393 a95b4f8 7e193fe db9a501 a95b4f8 7e193fe 1f6c393 a95b4f8 1f6c393 a95b4f8 1f6c393 75818ad 1f6c393 7e193fe db9a501 a95b4f8 819c345 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 |
import gradio as gr
from transformers import pipeline
import numpy as np
asr_model = "distil-whisper/distil-medium.en"
asr_pipe = pipeline("automatic-speech-recognition", model=asr_model)
def transcribe(stream, new_chunk):
sr, y = new_chunk
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, asr_pipe({"sampling_rate": sr, "raw": stream})["text"]
demo = gr.Blocks()
mic = gr.Interface(
fn = transcribe,
inputs = [
"state", gr.Audio(sources=["microphone"], streaming=True)],
outputs = ["state", "text"],
layout="horizontal",
theme="huggingface",
title="Whisper & BERT demo - Intent Classification",
description=(
"Transcribe audio inputs with Whisper ASR model and detect intention from the text. Use BERT NLP model to classify the intention as one of the commands to command a light."
),
allow_flagging="never",
live=True,
)
if __name__ == "__main__":
demo.launch()
|