Detect Silence using whsiper

YourAverageDev · 2023-11-11T20:46:26.133Z

Hello, I am pretty sure everyone here tried the ChatGPT mobile APP’s audio conversation system. I am curious how do they detect when the person stops speaking and send the Audio to Whisper. I am just curious how did they achieve this and if anyone can help, please send the script below. I code in python.

N2U · 2023-11-11T21:02:47.438Z

Hey champ!

Can’t just send you a script that will do that for you, you’ll have to write it yourself, so you’re sure it’ll work for you, but if you post your your progress I’m sure we can help you

Here’s a few hints to get you started:

you need some way of recording into a buffer.
Something to detect how long the silence lasts and cut it when it reaches a curtain threshold.

Which programming language are you working in?

_j · 2023-11-11T21:07:37.445Z

Here’s a cookbook if you’re at all into Python:

github.com

openai/openai-cookbook/blob/main/examples/Whisper_processing_guide.ipynb

{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Enhancing Whisper transcriptions: pre- & post-processing techniques\n",
    "\n",
    "This notebook offers a guide to improve the Whisper's transcriptions. We'll streamline your audio data via trimming and segmentation, enhancing Whisper's transcription quality. After transcriptions, we'll refine the output by adding punctuation, adjusting product terminology (e.g., 'five two nine' to '529'), and mitigating Unicode issues. These strategies will help improve the clarity of your transcriptions, but remember, customization based on your unique use-case may be beneficial.\n",
    "\n"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Setup\n",
    "\n",

This file has been truncated. show original