Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/ariym/whisper-node
Node.js bindings for OpenAI's Whisper. (C++ CPU version by ggerganov)
https://github.com/ariym/whisper-node
ai cpp ffmpeg ml nodejs openai typescript whisper
Last synced: 2 days ago
JSON representation
Node.js bindings for OpenAI's Whisper. (C++ CPU version by ggerganov)
- Host: GitHub
- URL: https://github.com/ariym/whisper-node
- Owner: ariym
- License: mit
- Created: 2022-12-18T00:48:06.000Z (about 2 years ago)
- Default Branch: master
- Last Pushed: 2024-08-05T03:52:59.000Z (5 months ago)
- Last Synced: 2024-12-14T01:05:57.010Z (9 days ago)
- Topics: ai, cpp, ffmpeg, ml, nodejs, openai, typescript, whisper
- Language: TypeScript
- Homepage: https://npmjs.com/whisper-node
- Size: 49.8 KB
- Stars: 245
- Watchers: 3
- Forks: 42
- Open Issues: 25
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# whisper-node
[](https://npmjs.org/package/whisper-node)
[](https://npmjs.org/package/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
```text
npm install whisper-node
```
2. Download whisper model of choice [OPTIONAL]
```text
npx whisper-node download
```
[Requirement for Windows: Install the ```make``` command from here.](https://gnuwin32.sourceforge.net/packages/make.htm)
## Usage
```javascript
import whisper from 'whisper-node';
const transcript = await whisper("example/sample.wav");
console.log(transcript); // output: [ {start,end,speech} ]
```
### Output (JSON)
```javascript
[
{
"start": "00:00:14.310", // time stamp begin
"end": "00:00:16.480", // time stamp end
"speech": "howdy" // transcription
}
]
```
### Full Options List
```javascript
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](https://ffmpeg.org) command: ```ffmpeg -i input.mp3 -ar 16000 output.wav```
## Made with
- [Whisper OpenAI (using C++ port by: ggerganov)](https://github.com/ggerganov/whisper.cpp)
- [ShellJS](https://www.npmjs.com/package/shelljs)
## Roadmap
- [x] Support projects not using Typescript
- [x] 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](https://www.npmjs.com/package/fluent-ffmpeg) to automatically convert to 16Hz .wav files as well as support separating audio from video
- [ ] [Pyanote diarization](https://huggingface.co/pyannote/speaker-diarization) for speaker names
- [ ] [Implement WhisperX as optional alternative model](https://github.com/m-bain/whisperX) for diarization and higher precision timestamps (as alternative to C++ version)
- [ ] Add option for viewing detected langauge as described in [Issue 16](https://github.com/ariym/whisper-node/issues/16)
- [ ] Include typescript typescript types in ```d.ts``` file
- [x] 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](https://ggerganov.com/)
- [Ari](https://aricv.com)