Hugging Face's logo
Saurav Panda's picture
1 2 55

Saurav Panda

sauravpanda
21world's profile picture
ยท

AI & ML interests

Small models and edge runtime!

Recent Activity

liked a model about 19 hours ago
OuteAI/Lite-Mistral-150M-v2-Instruct
replied to Xenova's post 4 days ago
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: https://huggingface.co/spaces/webml-community/kokoro-web Link to models/samples: https://huggingface.co/onnx-community/Kokoro-82M-ONNX You can get started in just a few lines of code! ```js 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
replied to Xenova's post 4 days ago
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: https://huggingface.co/spaces/webml-community/kokoro-web Link to models/samples: https://huggingface.co/onnx-community/Kokoro-82M-ONNX You can get started in just a few lines of code! ```js 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
View all activity

Organizations

Cloud Code AI's profile picture SmallEval's profile picture

sauravpanda's activity

liked a model about 19 hours ago
replied to Xenova's post 4 days ago
view reply

I am currently developing a library aimed at enabling llms inside the browser. It's essentially a wrapper for MLC and transformer.js right now but plan to add more agentic stuff like RAG etc.

To integrate transformer.js with Next.js, I had to convert it to TypeScript. I want to ensure that I properly credit you and your work, and you can check it out here: https://github.com/sauravpanda/BrowserAI.

Additionally, I noticed that the license in transformer.js appears to be incomplete and contains default values. I wanted to bring this to your attention.

I hope this is okay with you, and I truly admire all of your work!
replied to Xenova's post 4 days ago
liked a model 5 days ago
updated a model 6 days ago
published a model 6 days ago
liked a model 7 days ago
updated a dataset 7 days ago
published a dataset 7 days ago
liked 2 models 7 days ago
liked a model 12 days ago
liked 2 Spaces 18 days ago
liked a model 18 days ago
updated 3 models 19 days ago
reacted to m-ric's post with ๐Ÿ”ฅ 19 days ago
view post
Post
5049
Since I published it on GitHub a few days ago,
Hugging Face's new agentic library ๐˜€๐—บ๐—ผ๐—น๐—ฎ๐—ด๐—ฒ๐—ป๐˜๐˜€ has gathered nearly 4k stars ๐Ÿคฏ

โžก๏ธ But we are just getting started on agents: so we are hiring an ML Engineer to join me and double down on this effort!

The plan is to build GUI agents: agents that can act on your computer with mouse & keyboard, like Claude Computer Use.

We will make it work better, and fully open. โœจ

Sounds like something you'd like to do? Apply here ๐Ÿ‘‰ https://apply.workable.com/huggingface/j/AF1D4E3FEB/
ยท
replied to m-ric's post 19 days ago
view reply

I love this idea, I am also starting a project using transformer.js to automate things in browsers like computer use. I would love to see if you guys have any plans for the same.