Hugging Face's logo
Activity Feed Request to join this org

AI & ML interests

Building interactive demos to scikit-learn examples 🧑

Recent Activity
EduardoPachecoΒ  authored a paper about 1 month ago
RVQ Position Aware Speculative Decoding for On Device Text to Speech
EduardoPachecoΒ  authored a paper about 2 months ago
Taming Long-form Text-to-Speech
Q-bertΒ  authored a paper 3 months ago
ARCHead: Activation-Metric Residual Correction for Large Language Model Output Heads
View all activity
ZennyKennyΒ 
posted an update 4 days ago
view post
Post
1,890
Trying to train a locally deployable model on a LoRa adapter that's just wicked strong at running sec evals on PRs because these general purpose code review solutions always seem to miss glaring security stuff.

The clear finding from the v1 training run was that "less code = more secure" lmfao.

Model basically scores functions better the less stuff they do. It's right I guess in a kind of demented way. Pack it up boys, we've got the solution.
  • 6 replies
Β·
TonicΒ 
posted an update 10 days ago
view post
Post
366
πŸ‘‹Hey there folks ,

I wanted to use a Jev model in a practical way , and I came up with this OCR pipeline using decision-models to evaluate OCR quality .

Check it out :

Tonic/OCR-with-JEV
  • 1 reply
Β·
ZennyKennyΒ 
posted an update 20 days ago
NymboΒ 
posted an update 26 days ago
view post
Post
3,841
Introducing Live Subtitles, a Windows tray app that captions anything your PC is playing and isn't butt ugly. live and fully local. It runs NVIDIA's Parakeet-unified 0.6B on your GPU, puts words on screen about 0.36 s after they're spoken, and uses less than one CPU core while it does it.

I built a benchmark for it out of real TV, podcasts, earnings calls and a short film. Parakeet-unified scores 12.1% WER there, close to Nemotron streaming's 11.4%, but with much better punctuation and lower worst-case delay. Once a caption is on screen it never gets rewritten or jumps lines, and the overlay disappears when nobody's talking.

No NVIDIA GPU? It falls back to Nemotron on the CPU, which also covers 30 other languages. It can also write SRT/ASS/VTT files for videos on disk.

Windows only. The GPU engine needs an NVIDIA card with ~3.2 GB of free VRAM. MIT.

Edit: the first version of this post said 13.8% vs 17.0%. The replies caught a scoring bug (numbers weren't normalized), so the benchmark now uses Whisper's English normalizer and the numbers above are re-scored.

Get it here:
https://github.com/Nymbo/Live-Subtitles

Models:
nvidia/parakeet-unified-en-0.6b
nvidia/nemotron-speech-streaming-en-0.6b
  • 7 replies
Β·
Aurelien-MorganΒ 
posted an update 2 months ago
view post
Post
2,474
@retrain-pipelines execution engine is in perpetual evolution, with the aim to establish itself as SOTA, and for the long run.

However, we neglect no aspect of ML-Eng centricity.

If notebooks is where you like to do dev most,
we support you there 100% too.

Build crazy combos of inline tasks, deep parallel sub-DAG branches, nested asynchronous groups...

... the DAG renderer is undergoing an incremental upgrade

until the next one.

* starring toy tasks here. No ML has been hurt in this video πŸ™‚
NymboΒ 
posted an update 3 months ago
view post
Post
2,676
Anthropic gave me six months of Claude Max 20x through the Claude for Open Source program, granted based on my Hugging Face work. Thank you
Anthropic for supporting open source.

So far I've been pointing it at Markdown Minimap, an Obsidian plugin that adds a scrollable IDE-style minimap to your notes. This week I've been clearing a backlog of user-reported issues on it, with Claude often handling them end to end.

https://github.com/Nymbo/Markdown-Minimap β€” issues and PRs welcome.
Q-bertΒ 
authored a paper 3 months ago
NymboΒ 
posted an update 4 months ago
view post
Post
6,218
Introducing Inflect-v2, two exceptionally small, open-weight English TTS models at just 3.9M and 9.3M parameters. Both generate speech multiple times faster than real-time on CPU. Despite their size, Inflect-v2 delivers quality that is competitive with much larger lightweight TTS systems, including KittenTTS, Piper, and Supertonic-3.

CPU, CUDA, PyTorch, and ONNX are supported. Apache 2.0.

See it for yourselves:
owensong/Inflect-Micro-v2
owensong/Inflect-Nano-v2

Try the Demos:
Nymbo/Inflect-TTS (unlimited CPU usage)
owensong/Inflect-v2 (ultra-fast ZeroGPU usage)
  • 6 replies
Β·
PhysiQuantyΒ 
posted an update 4 months ago
view post
Post
5,373
🧠 Arithmetic-SLM : A 30M model that manages to compute simple arithmetic better than a 3B model πŸš€
WhirlwindAI/Arithmetic-SLM
WhirlwindAI/arithmetic-slm

πŸ† Leaderboard ArithMark-2 πŸ†
πŸ₯‡ Qwen/Qwen2.5-Math-1.5B = 82.08%
πŸ₯ˆ WhirlwindAI/Arithmetic-SLM = 78.60% (31.7M Params)
πŸ₯‰ Qwen/Qwen2.5-3B = 78.44%

Example WhirlwindAI/Arithmetic-SLM =
0.5 * 0.5 = 0.25 βœ…
105 + 45 / 8 = 110 βœ…
(132 / 12) + (46 - 15) = 42 βœ…
(10 + 28) * 3 = 114 βœ…
1 * (16 + 28) = 44 βœ…
(21 + 27) * (14 - 7) = 336 ❌ 

leaderboard = """
|              Model               |    Params    |   Score   |
|----------------------------------|--------------|-----------|
|      Qwen/Qwen2.5-Math-1.5B      |     1.54B    |   82.08%  |
|    WhirlwindAI/Arithmetic-SLM    |    31.70M    |   78.60%  | <=
|         Qwen/Qwen2.5-3B          |     3.09B    |   78.44%  |
|        Qwen/Qwen2.5-1.5B         |     1.54B    |   77.72%  |
|    Qwen/Qwen2.5-Coder-1.5B       |     1.54B    |   74.88%  |
|   HuggingFaceTB/SmolLM2-1.7B     |     1.71B    |   66.12%  |
|        Qwen/Qwen2.5-0.5B         |      494M    |   63.04%  |
| facebook/MobileLLM-R1-140M-base  |      140M    |   53.88%  |
|     SupraLabs/Supra-50M-Base     |       52M    |   27.12%  |
"""

Bench =
AxiomicLabs/ArithMark-2.0
DataSet =
WhirlwindAI/Arithmetic
By Science AND FOR SCIENCE <3
  • 3 replies
Β·
eienmojikiΒ 
posted an update 5 months ago
PhysiQuantyΒ 
posted an update 6 months ago
view post
Post
5,538
🌐 We crawled the entirety of Hugging Face to help the community! Huge thanks to the Hugging Face API 🌐
πŸ€– 2.91M model repos (file names included), πŸ“š 1.02M dataset repos, πŸš€ 1.31M Space repos
πŸ€— 617,501 committers (datasets and models), we’ll share Hugging Face statistics with you in the coming days..

We also identified 61,398 users with β€œAI/ML Interests”, and NOW we can find each other through our β€œAI/ML Interestsβ€πŸ€—
HF-Collab-Center/Searching-For-HuggingFace-Users
HF-Collab-Center/All-Model-Repos
HF-Collab-Center/All-Dataset-Repos
HF-Collab-Center/All-Space-Repos

HF-Collab-Center/HF-Users
HF-Collab-Center/HF-Users-with-last-seen
HF-Collab-Center/HF-Users-With-AI-ML-Interests-Only

Made By @QuantaSparkLabs and @PhysiQuanty
C'est français, bon.. en anglais.. mais c'est français ;)
  • 5 replies
Β·
PhysiQuantyΒ 
posted an update 6 months ago
johkoΒ 
posted an update 6 months ago
view post
Post
274
One prompt, three answers - which model is from where?

johko/llm-blind-date

I built a little demo where you give three models (Apertus, Llama, Qwen3) the same prompt and in the end you have to guess which is which just based on their answers.

GIve it a try! ;)
PhysiQuantyΒ 
posted an update 6 months ago
view post
Post
5,178
❗ Dating apps do not allow us to control the profiles suggested to us based on our mutual search criteria ❗
🧬 If you want to see if your soulmate has already existed, I have published a dataset of 59k anonymized public profiles

SpiceeChat/OkCupid-59k-Anonymized-Profiles

Are you looking for a female ML engineer who is looking for a male ML engineer and you can't find it on the apps ?
You need to look for her, but more importantly, she needs to look for you.
Personally, I'm looking for a physicist I'm encountering the same problem. I can't find it
My answer : Paradox of choice of dating apps solved by patent ⚑

J'ai du brevetΓ© pour te trouver et on se trouvera bientΓ΄t !
  • 9 replies
Β·
TonicΒ 
posted an update 6 months ago
view post
Post
3,560
πŸ™‹πŸ»β€β™‚οΈ Hey there folks ,

Turns out : if we predict 🌏 earth we can save a lot of time looking for interesting things and less time looking at things that we expect to see.

Sentinel-2 imagery πŸ›°οΈbasically takes a long time to download towards earth. so our "near real time" systems are quite far from that in practical terms.

meanwhile , if we "predict" what we will see , based on what we do see , we can send down much less data in a timely way , and prioritize πŸ“‘earth-bound response .

I'm talking about illegal fishing , logging , mining or building in nature reserves , the more of that we predict early the more we're able to stop it on time.

At least that's the concept !

check out the blog : https://huggingface.co/blog/Tonic/save-patagonia-by-predicting-earth


- Collection: https://huggingface.co/collections/NuTonic/earth-observation-with-temporal-and-general-understanding
- Code: https://github.com/Josephrp/Nutonic
- Dataset: NuTonic/sat-vl-sft-training-ready-v1
- Model: NuTonic/lspace
- Training: NuTonic/lspace-trackio
- Evals: NuTonic/Patagonia_Eval
  • 3 replies
Β·
Aurelien-MorganΒ 
posted an update 6 months ago
view post
Post
1,150
@retrain-pipelines v0.2.0 is out !
I'm at Station F at My booth with GOSIM Paris 2026 today & tomorrow.
Come meet me for a live in-person demo and a chat !
  • 1 reply
Β·
TonicΒ 
posted an update 7 months ago
view post
Post
4,527
πŸ™‹πŸ»β€β™‚οΈ Hey there folks,

since everyone liked my previous announcement post ( https://huggingface.co/posts/Tonic/338509028435394 ) so much , i'm back with more high quality proceedural datasets in the Geospacial domain for SFT training !

Check this one out :
NuTonic/sat-bbox-metadata-sft-v1

the goal is to be able to train vision models on multiple images for remote sensing analysis with one shot .

hope you like it ! πŸš€
  • 2 replies
Β·
TonicΒ 
posted an update 7 months ago
view post
Post
3,769
πŸ™‹πŸ»β€β™‚οΈ Hey there folks ,

I'm sharing huggingface's largest dataset of annotated statelite images today.

check it out here : NuTonic/sat-image-boundingbox-sft-full

I hope you like it , the idea is to be able to use this with small vision models πŸš€
MElHuseyniΒ 
authored a paper 7 months ago
MElHuseyniΒ 
submitted a paper to Daily Papers 7 months ago