ChetanXpro / nodejs-whisper

NodeJS Bindings for Whisper - the CPU version of OpenAI's Whisper, as initially crafted in C++ by ggerganov.
https://npmjs.com/nodejs-whisper
MIT License
93 stars 22 forks source link
ai cpp ml nodejs-whisper openai speech-recognition speech-to-text timestamp whisper whisper-nodejs

nodejs-whisper

Node.js bindings for OpenAI's Whisper model.

MIT License

Features

Installation

  1. Install make tools
sudo apt update
sudo apt install build-essential
  1. Install nodejs-whisper with npm
  npm i nodejs-whisper
  1. Download whisper model
  npx nodejs-whisper download

Usage/Examples

import path from 'path'
import { nodewhisper } from 'nodejs-whisper'

// Need to provide exact path to your audio file.
const filePath = path.resolve(__dirname, 'YourAudioFileName')

await nodewhisper(filePath, {
    modelName: 'base.en', //Downloaded models name
    autoDownloadModelName: 'base.en', // (optional) autodownload a model if model is not present
    verbose: false, // (optional) output more dubugging information
    removeWavFileAfterTranscription: false, // (optional) remove wav file once transcribed
    withCuda: false // (optional) use cuda for faster processing
    whisperOptions: {
        outputInCsv: false, // get output result in csv file
        outputInJson: false, // get output result in json file
        outputInJsonFull: false, // get output result in json file including more information
        outputInLrc: false, // get output result in lrc file
        outputInSrt: true, // get output result in srt file
        outputInText: false, // get output result in txt file
        outputInVtt: false, // get output result in vtt file
        outputInWords: false, // get output result in wts file for karaoke
        translateToEnglish: false, // translate from source language to english
        wordTimestamps: false, // word-level timestamps
        timestamps_length: 20, // amount of dialogue per timestamp pair
        splitOnWord: true, // split on word rather than on token
    },
})

// Model list
const MODELS_LIST = [
    'tiny',
    'tiny.en',
    'base',
    'base.en',
    'small',
    'small.en',
    'medium',
    'medium.en',
    'large-v1',
    'large',
]

Types

 interface IOptions {
    modelName: string
    verbose?: boolean
    removeWavFileAfterTranscription?: boolean
    withCuda?: boolean
    autoDownloadModelName?: string
    whisperOptions?: WhisperOptions
}

 interface WhisperOptions {
    outputInCsv?: boolean
    outputInJson?: boolean
    outputInJsonFull?: boolean
    outputInLrc?: boolean
    outputInSrt?: boolean
    outputInText?: boolean
    outputInVtt?: boolean
    outputInWords?: boolean
    translateToEnglish?: boolean
    timestamps_length?: number
    wordTimestamps?: boolean
    splitOnWord?: boolean
}

Run locally

Clone the project

  git clone https://github.com/ChetanXpro/nodejs-whisper

Go to the project directory

  cd nodejs-whisper

Install dependencies

  npm install

Start the server

  npm run dev

Build project

  npm run build

Made with

Feedback

If you have any feedback, please reach out to us at chetanbaliyan10@gmail.com

Authors