scott/kokoro
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update Kokoro.js: WebGPU support, v1.0 integration (#60)

Browse Source 
* Set up JS project

* Finalise JS library

* Update README

* Fix package.json repository url

* Rename package -> `kokoro-js`

* Fix samples in README

* Cleanup README

* Bump `phonemizer` version

* Create web demo

* Run prettier

* Link to model used in demo

* Enable multithreading in HF space demo (~40% faster)

* Add link to demo in README

* Bump to v1.0.1

* Update voices

* Update versions

* Update phonemize JSDoc

* Use updated voice pack

* Update versions

* Update demo (v1.0 & WebGPU support)

* Update README

* Enforce maximum number of tokens

* Update README

* [version] Update to 1.1.1
This commit is contained in:
Joshua Lochner
2025-02-07 20:04:41 +02:00
committed by GitHub
parent 31a2b6337b
commit e0bf641def
65 changed files with 1242 additions and 164 deletions
Download Patch File Download Diff File Expand all files Collapse all files

62
kokoro.js/README.md
View File

@@ -5,10 +5,10 @@
<a href="https://www.npmjs.com/package/kokoro-js"><img alt="NPM Downloads" src="https://img.shields.io/npm/dw/kokoro-js"></a>
<a href="https://www.jsdelivr.com/package/npm/kokoro-js"><img alt="jsDelivr Hits" src="https://img.shields.io/jsdelivr/npm/hw/kokoro-js"></a>
<a href="https://github.com/hexgrad/kokoro/blob/main/LICENSE"><img alt="License" src="https://img.shields.io/github/license/hexgrad/kokoro?color=blue"></a>
<a href="https://huggingface.co/spaces/webml-community/kokoro-web"><img alt="Demo" src="https://img.shields.io/badge/Hugging_Face-demo-green"></a>
<a href="https://huggingface.co/spaces/webml-community/kokoro-webgpu"><img alt="Demo" src="https://img.shields.io/badge/Hugging_Face-demo-green"></a>
</p>
Kokoro is a frontier TTS model for its size of 82 million parameters (text in/audio out). This JavaScript library allows the model to be run 100% locally in the browser thanks to [🤗 Transformers.js](https://huggingface.co/docs/transformers.js). Try it out using our [online demo](https://huggingface.co/spaces/webml-community/kokoro-web)!
Kokoro is a frontier TTS model for its size of 82 million parameters (text in/audio out). This JavaScript library allows the model to be run 100% locally in the browser thanks to [🤗 Transformers.js](https://huggingface.co/docs/transformers.js). Try it out using our [online demo](https://huggingface.co/spaces/webml-community/kokoro-webgpu)!
## Usage
@@ -23,33 +23,59 @@ You can then generate speech as follows:
```js
import { KokoroTTS } from "kokoro-js";
const model_id = "onnx-community/Kokoro-82M-ONNX";
const model_id = "onnx-community/Kokoro-82M-v1.0-ONNX";
const tts = await KokoroTTS.from_pretrained(model_id, {
dtype: "q8", // Options: "fp32", "fp16", "q8", "q4", "q4f16"
device: "wasm", // Options: "wasm", "webgpu" (web) or "cpu" (node). If using "webgpu", we recommend using dtype="fp32".
});
const text = "Life is like a box of chocolates. You never know what you're gonna get.";
const audio = await tts.generate(text, {
// Use `tts.list_voices()` to list all available voices
voice: "af_bella",
voice: "af_heart",
});
audio.save("audio.wav");
```
## Voices/Samples
> Life is like a box of chocolates. You never know what you're gonna get.
> [!TIP]
> You can find samples for each of the voices in the [model card](https://huggingface.co/onnx-community/Kokoro-82M-v1.0-ONNX#samples) on Hugging Face.
| Voice | Nationality | Gender | Sample |
| ------------------------ | ----------- | ------ | -------------------------------------------------------------------------------------------------------- |
| Default (`af`) | American | Female | <video controls src="https://github.com/user-attachments/assets/c183df83-58a9-4aea-8fdf-225092acec57" /> |
| Bella (`af_bella`) | American | Female | <video controls src="https://github.com/user-attachments/assets/0730fff0-22b3-458f-9675-36d313d872d6" /> |
| Nicole (`af_nicole`) | American | Female | <video controls src="https://github.com/user-attachments/assets/4ce0b3f6-eaec-4e47-901c-9d29e2b60c86" /> |
| Sarah (`af_sarah`) | American | Female | <video controls src="https://github.com/user-attachments/assets/d37dba3f-de59-44c4-bc3d-da91ea1b5a4a" /> |
| Sky (`af_sky`) | American | Female | <video controls src="https://github.com/user-attachments/assets/38230be5-881c-4407-81e6-a0b1e4101565" /> |
| Adam (`am_adam`) | American | Male | <video controls src="https://github.com/user-attachments/assets/66a4c439-e80b-4c91-8a27-ae094486a2d8" /> |
| Michael (`am_michael`) | American | Male | <video controls src="https://github.com/user-attachments/assets/79a8879d-b564-4222-b2d5-a97f783ae897" /> |
| Emma (`bf_emma`) | British | Female | <video controls src="https://github.com/user-attachments/assets/ad5eb254-1d84-4282-9d23-371d5765d820" /> |
| Isabella (`bf_isabella`) | British | Female | <video controls src="https://github.com/user-attachments/assets/ea7e6825-dad0-403c-9ece-680af04f5a25" /> |
| George (`bm_george`) | British | Male | <video controls src="https://github.com/user-attachments/assets/e09040aa-578f-40a6-b7fd-76a5b005346c" /> |
| Lewis (`bm_lewis`) | British | Male | <video controls src="https://github.com/user-attachments/assets/5d7b26bf-8900-4a9a-8ee5-a16c39bb834c" /> |
### American English
| Name | Traits | Target Quality | Training Duration | Overall Grade |
| ------------ | ------ | -------------- | ----------------- | ------------- |
| **af_heart** | 🚺❤️ | | | **A** |
| af_alloy | 🚺 | B | MM minutes | C |
| af_aoede | 🚺 | B | H hours | C+ |
| af_bella | 🚺🔥 | **A** | **HH hours** | **A-** |
| af_jessica | 🚺 | C | MM minutes | D |
| af_kore | 🚺 | B | H hours | C+ |
| af_nicole | 🚺🎧 | B | **HH hours** | B- |
| af_nova | 🚺 | B | MM minutes | C |
| af_river | 🚺 | C | MM minutes | D |
| af_sarah | 🚺 | B | H hours | C+ |
| af_sky | 🚺 | B | _M minutes_ 🤏 | C- |
| am_adam | 🚹 | D | H hours | F+ |
| am_echo | 🚹 | C | MM minutes | D |
| am_eric | 🚹 | C | MM minutes | D |
| am_fenrir | 🚹 | B | H hours | C+ |
| am_liam | 🚹 | C | MM minutes | D |
| am_michael | 🚹 | B | H hours | C+ |
| am_onyx | 🚹 | C | MM minutes | D |
| am_puck | 🚹 | B | H hours | C+ |
| am_santa | 🚹 | C | _M minutes_ 🤏 | D- |
### British English
| Name | Traits | Target Quality | Training Duration | Overall Grade |
| ----------- | ------ | -------------- | ----------------- | ------------- |
| bf_alice | 🚺 | C | MM minutes | D |
| bf_emma | 🚺 | B | **HH hours** | B- |
| bf_isabella | 🚺 | B | MM minutes | C |
| bf_lily | 🚺 | C | MM minutes | D |
| bm_daniel | 🚹 | C | MM minutes | D |
| bm_fable | 🚹 | B | MM minutes | C |
| bm_george | 🚹 | B | MM minutes | C |
| bm_lewis | 🚹 | C | H hours | D+ |