Audio Transcription Project

This project enables users to transcribe audio files into text using the Whisper ASR (Automatic Speech Recognition) library. It consists of a Flask application in Python for transcription and an Express.js application in Node.js for file uploads.

Documentation

Whisper Documents

Run Locally

Donwload Python

  https://www.python.org/downloads/

Whisper Package

  pip install -U openai-whisper

It also requires the command-line tool ffmpeg to be installed on your system, which is available from most package managers:

  choco install ffmpeg

Clone the project

  git clone https://github.com/krishnadobhal/Speech-to-text--nodejs--any-language.git

Install dependencies

  npm install

Start the server

  node app.js

  python main.py