codenamev / whisper-node

NodeJS bindings for OpenAI's Whisper. (C++ CPU version by ggerganov)

whisper-node

Node.js bindings for OpenAI's Whisper. Transcription done local.

Features

• Output transcripts to JSON (also .txt .srt .vtt)
• Optimized for CPU (Including Apple Silicon ARM)
• Timestamp precision to single word

Installation

1. Add dependency to project

npm install whisper-node

2. Download whisper model of choice [OPTIONAL]

npx whisper-node download

Requirement for Windows: Install the make command from here.

Usage

import whisper from 'whisper-node';

const transcript = await whisper("example/sample.wav");

console.log(transcript); // output: [ {start,end,speech} ]

Output (JSON)

[
  {
    "start":  "00:00:14.310", // time stamp begin
    "end":    "00:00:16.480", // time stamp end
    "speech": "howdy"         // transcription
  }
]

Full Options List

import whisper from 'whisper-node';

const filePath = "example/sample.wav"; // required

const options = {
  modelName: "base.en",       // default
  // modelPath: "/custom/path/to/model.bin", // use model in a custom directory (cannot use along with 'modelName')
  whisperOptions: {
    language: 'auto'          // default (use 'auto' for auto detect)
    gen_file_txt: false,      // outputs .txt file
    gen_file_subtitle: false, // outputs .srt file
    gen_file_vtt: false,      // outputs .vtt file
    word_timestamps: true     // timestamp for every word
    // timestamp_size: 0      // cannot use along with word_timestamps:true
  }
}

const transcript = await whisper(filePath, options);

Input File Format

Files must be .wav and 16Hz

Example .mp3 file converted with an FFmpeg command: ffmpeg -i input.mp3 -ar 16000 output.wav

Made with

• Whisper OpenAI (using C++ port by: ggerganov)
• ShellJS

Roadmap

• Support projects not using Typescript
• Allow custom directory for storing models
• Config files as alternative to model download cli
• Remove path, shelljs and prompt-sync package for browser, react-native expo, and webassembly compatibility
• fluent-ffmpeg to automatically convert to 16Hz .wav files as well as support separating audio from video
• Pyanote diarization for speaker names
• Implement WhisperX as optional alternative model for diarization and higher precision timestamps (as alternative to C++ version)
• Add option for viewing detected langauge as described in Issue 16
• Include typescript typescript types in d.ts file
• Add support for language option
• Add support for transcribing audio streams as already implemented in whisper.cpp

Modifying whisper-node

npm run dev - runs nodemon and tsc on '/src/test.ts'

npm run build - runs tsc, outputs to '/dist' and gives sh permission to 'dist/download.js'

Acknowledgements

• Georgi Gerganov
• Ari