Carsen Klock's picture

Carsen Klock PRO

carsenk

AI & ML interests

Don't be afraid of AI, be afraid of ignoring it.

Recent Activity

liked a model 4 days ago
deepseek-ai/DeepSeek-V3-0324
liked a model 15 days ago
tencent/Hunyuan3D-2
liked a model 24 days ago
unsloth/Llama-3.2-1B-Instruct-GGUF
View all activity

Organizations

MLX Community's profile picture Cognitive Computations's profile picture

carsenk's activity

upvoted an article about 1 month ago
view article
Article

Open-source DeepResearch โ€“ Freeing our search agents

โ€ข 1.19k
reacted to Xenova's post with ๐Ÿ”ฅ about 2 months ago
view post
Post
6733
Introducing Kokoro.js, a new JavaScript library for running Kokoro TTS, an 82 million parameter text-to-speech model, 100% locally in the browser w/ WASM. Powered by ๐Ÿค— Transformers.js. WebGPU support coming soon!
๐Ÿ‘‰ npm i kokoro-js ๐Ÿ‘ˆ

Try it out yourself: webml-community/kokoro-web
Link to models/samples: onnx-community/Kokoro-82M-ONNX

You can get started in just a few lines of code!
import { KokoroTTS } from "kokoro-js";

const tts = await KokoroTTS.from_pretrained(
  "onnx-community/Kokoro-82M-ONNX",
  { dtype: "q8" }, // fp32, fp16, q8, q4, q4f16
);

const text = "Life is like a box of chocolates. You never know what you're gonna get.";
const audio = await tts.generate(text,
  { voice: "af_sky" }, // See `tts.list_voices()`
);
audio.save("audio.wav");

Huge kudos to the Kokoro TTS community, especially taylorchu for the ONNX exports and Hexgrad for the amazing project! None of this would be possible without you all! ๐Ÿค—

The model is also extremely resilient to quantization. The smallest variant is only 86 MB in size (down from the original 326 MB), with no noticeable difference in audio quality! ๐Ÿคฏ
ยท