Rasmus Aagaard's picture

Rasmus Aagaard

rasgaard

AI & ML interests

Interested in using LLMs in products, evaluation of those products and small models

Recent Activity

View all activity

Organizations

Hugging Face Discord Community's profile picture

rasgaard's activity

reacted to Xenova's post with πŸ”₯ 9 days ago
view post
Post
3017
NEW: Real-time conversational AI models can now run 100% locally in your browser! 🀯

πŸ” Privacy by design (no data leaves your device)
πŸ’° Completely free... forever
πŸ“¦ Zero installation required, just visit a website
⚑️ Blazingly-fast WebGPU-accelerated inference

Try it out: webml-community/conversational-webgpu

For those interested, here's how it works:
- Silero VAD for voice activity detection
- Whisper for speech recognition
- SmolLM2-1.7B for text generation
- Kokoro for text to speech

Powered by Transformers.js and ONNX Runtime Web! πŸ€— I hope you like it!
Β·
reacted to yeonseok-zeticai's post with πŸ”₯ 10 days ago
view post
Post
2016
πŸš€ NEW DROP: run your own on-device LLMβ€”in minutes, on any phone
Today we’re open-sourcing everything you need to put Qwen3-0.6B straight into a production-ready mobile app:

πŸŽ₯ Watch Qwen3-0.6B chat in real time on any smartphones!

πŸ“Š TPS benchmarks – slides comparing token-per-second across heterogeneous mobile devices

πŸ’» Plug-and-play source – Just Copy & Run the source to your project for Android (Kotlin & Java) and iOS (Swift).

🀞 Cross-platform, one pipeline – ZETIC.MLange auto-tunes kernels for every different devices, we’ve tested.

πŸ‘¨β€πŸ’» Ready for production – swap in your own model, re-benchmark with one command, publish.

Get started
Just Sign-up and check the playground project, QWEN-0.6B
- https://mlange.zetic.ai/p/zetic-example/Qwen3-0.6B

We built this to show that cloud-free LLMs are ready today. Dive in, fork it, and tag ZETIC.ai when you launch your own on-device assistant, game NPC, or offline content generatorβ€”we’ll spotlight the best projects.
upvoted an article 10 days ago
view article
Article

AI Policy @πŸ€—: Response to the 2025 National AI R&D Strategic Plan

By evijit and 2 others β€’
β€’ 12
reacted to Xenova's post with πŸ”₯ 15 days ago
view post
Post
7908
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 πŸ€— Transformers.js. WebGPU support coming soon!
πŸ‘‰ npm i kokoro-js πŸ‘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! πŸ€—

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! 🀯
Β·
published an article 19 days ago
upvoted 2 articles about 1 month ago
view article
Article

Blazingly fast whisper transcriptions with Inference Endpoints

By mfuntowicz and 5 others β€’
β€’ 69
view article
Article

Vision Language Models (Better, Faster, Stronger)

By merve and 4 others β€’
β€’ 437
New activity in CoRal-project/roest-wav2vec2-315m-v1 about 2 months ago

Convert to ONNX

6
#1 opened about 2 months ago by
PierreMesure
reacted to Xenova's post with πŸ”₯ about 2 months ago