Hugging Face's logo

ONNXConfig for all
non-profit
Activity Feed Request to join this org

AI & ML interests

Make all hub models available for conversion to ONNX format.
Nymboย 
posted an update 14 days ago
view post
Post
3,742
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
ยท
MaziyarPanahiย 
posted an update 18 days ago
AtAndDevย 
posted an update 22 days ago
view post
Post
5,281
@Banaxi-Tech stop hiding my comments. AND STOP STEALING PAPERS AND SPREADING MISINFORMATION.
your BGA blog is a copy of NSA (deepseek, 2025) branded under your name. literally the same top16 selected blocks, 512 local window, router over block summaries, all you did was change block size from 64 to 128.
you didnt cite NSA once but you put a โ€œplease cite BGAโ€ bibtex at the bottom.
i commented under your post and said that there is no way that you can support claims like: โ€œThe Accuracy Should BE WAy better than DSA but untested yet.โ€ you didnt run a single experiment. and the 256x isnt from BGA, its just n/2k with k=2048 so the exact same k DSA uses. if opus wrote this for you, at least read it before posting.
i commented again after you hid my comment despite it having constructive and correct feedback and you hid that too. and again.
you can hide the truth and just try to get hf post likes..... but is it really the thing that needs to be done? do you really want to take papers and make them yours while barely even changing the params?

admitting your mistakes and doing something about them needs humbleness, intelligence, humanness.
i encourage you to admit your mistakes and try to do better next time (at least read what blog your ai wrote or do proper experiments to back your stuff up).
  • 49 replies
ยท
Aurelien-Morganย 
posted an update about 2 months ago
view post
Post
2,468
@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 ๐Ÿ™‚
AtAndDevย 
posted an update 2 months ago
view post
Post
2,957
SPECK 2 IS ALREADY OUT: specklabs/Speck2-140M

Pretrained on 4x more tokens than the previous releases (20b vs 5b).
Instruct tuned versions are coming soon.
Very interesting models are coming soon too (hint: super long context).

Thanks for everyone supporting!
  • 3 replies
ยท
AtAndDevย 
posted an update 2 months ago
view post
Post
218
SPECK1.5 IS COMING SOON!
Same 5B token budget but much better corpus quality.

Also getting a ton of downloads, thanks for everyone downloading and liking <3

specklabs
AtAndDevย 
posted an update 2 months ago
view post
Post
164
NEW SPECK UPDATES:

Just hit #14 and #15 with out FIRST models on Open SLM Leaderboard. The models were trained on 5B tokens, while competing with similarly sized models trained on more than 6-20x the data.

A new base model Speck1.5-140M being trained right now on a higher quality corpus and will be released soon.
SpeckChat3 is coming very soon with 1 million samples, specifically designed to post train small base models.

Also, just to clarify stuff, we will NOT release anything that is NOT MIT licensed EVER. Openness is needed in small language research.

Thanks to everyone supporting the project, and stay tuned for new releases!
AtAndDevย 
posted an update 2 months ago
view post
Post
1,898
SPECK UPDATES:
1 New instruct model tuned on top of Speck1-140M: specklabs/Speck1-140M-Instruct
2 Instruction tuning datasets
2 GGUFs

Much more coming soon:
Speck1.1-140M-Instruct that is post trained on SpeckChat2 will be coming very soon
New base model Speck1.5-140M is coming with a much higher quality corpus

Thanks to everyone who is already supporting the project, and stay tuned for new releases!
  • 3 replies
ยท
AtAndDevย 
posted an update 2 months ago
view post
Post
2,133
FIRST SPECK MODEL RELEASED:
specklabs/Speck1-140M

new models coming very soon (both instruct and much better models), with much much higher training scale as i am getting marenostrum5 access soon!
we will be looking at 100b-2t token budgets :)
  • 4 replies
ยท
Nymboย 
posted an update 3 months ago
view post
Post
2,604
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 โ€” issues and PRs welcome.
Nymboย 
posted an update 3 months ago
view post
Post
6,206
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
ยท
espejelomarย 
posted an update 6 months ago
view post
Post
4,788
Sharing WorldForge with @abdelstark

It's an open-source Python project for evaluating and replaying robotics and world-model workflows.

The useful part is not only calling a model. WorldForge records the run, validates action shapes, translates outputs into actions, and keeps replay artifacts you can inspect later.

The current demo uses LeRobot + LeWorldModel on PushT through the official loader:

stable_worldmodel.policy.AutoCostModel("pusht/lewm")

The harness also has replay-only paths for Cosmos-Policy and GR00T-style outputs, so you can inspect the provider contract from saved artifacts without keeping a GPU server online.

Try it:

pip install worldforge-ai
uv run --extra harness worldforge-harness --flow robotics-compare

Repo: https://github.com/AbdelStark/worldforge
Docs: https://abdelstark.github.io/worldforge/

Pre-1.0, MIT, and actively looking for contributors. Good areas:
- robotics provider adapters
- replay artifacts
- eval flows
- docs & first-run demos

Good first issues: https://github.com/AbdelStark/worldforge/contribute

If you're building robot policy evals or model adapters, would love a PR โ€” or an issue describing what's missing.
Aurelien-Morganย 
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
ยท
Aurelien-Morganย 
posted an update 7 months ago
view post
Post
241
Launching a workweek of @retrain-pipelines wheels.

Day #1 : Compose
  • 4 replies
ยท
MaziyarPanahiย 
posted an update 7 months ago
view post
Post
6,256
Training mRNA Language Models Across 25 Species for $165

We built an end-to-end protein AI pipeline covering structure prediction, sequence design, and codon optimization. After comparing multiple transformer architectures for codon-level language modeling, CodonRoBERTa-large-v2 emerged as the clear winner with a perplexity of 4.10 and a Spearman CAI correlation of 0.40, significantly outperforming ModernBERT. We then scaled to 25 species, trained 4 production models in 55 GPU-hours, and built a species-conditioned system that no other open-source project offers. Complete results, architectural decisions, and runnable code below.

https://huggingface.co/blog/OpenMed/training-mrna-models-25-species
  • 1 reply
ยท
MaziyarPanahiย 
posted an update 7 months ago
view post
Post
2,486
We annotated 119K medical images with two frontier VLMs (Qwen 3.5, Kimi K2.5), cross-validated at 93% agreement, and produced 110K training records, all for under $500. Fine-tuning 3 small models (2-3B params) improved all benchmarks: best model reaches +15.0% average exact match.

Everything is open-sourced: datasets, adapters, and code.

https://huggingface.co/blog/OpenMed/synthvision
  • 2 replies
ยท
Nymboย 
posted an update 8 months ago
view post
Post
8,016
We should really have a release date range slider on the /models page. Tired of "trending/most downloaded" being the best way to sort and still seeing models from 2023 on the first page just because they're embedded in enterprise pipelines and get downloaded repeatedly. "Recently Created/Recently Updated" don't solve the discovery problem considering the amount of noise to sift through.

Slight caveat: Trending actually does have some recency bias, but it's not strong/precise enough.
  • 3 replies
ยท
MaziyarPanahiย 
posted an update 8 months ago
view post
Post
5,057
DNA, mRNA, proteins, AI. I spent the last year going deep into computational biology as an ML engineer. This is Part I of what I found. ๐Ÿงฌ

In 2024, AlphaFold won the Nobel Prize in Chemistry.

By 2026, the open-source community had built alternatives that outperform it.

That's the story I find most interesting about protein AI right now. Not just the science (which is incredible), but the speed at which open-source caught up. Multiple teams, independently, reproduced and then exceeded AlphaFold 3's accuracy with permissive licenses. The field went from prediction to generation: we're not just modeling known proteins anymore, we're designing new ones.

I spent months mapping this landscape for ML engineers. What the architectures actually are (spoiler: transformers and diffusion models), which tools to use for what, and which ones you can actually ship commercially.

New post on the Hugging Face blog: https://huggingface.co/blog/MaziyarPanahi/protein-ai-landscape

Hope you all enjoy! ๐Ÿค—
  • 2 replies
ยท
MaziyarPanahiย 
authored a paper 8 months ago
MaziyarPanahiย 
posted an update 9 months ago
view post
Post
2,637
Announcing: OpenMed Multilingual PII Detection Models

Today I am releasing 105 open-source models for Personally Identifiable Information (PII) detection in French, German, and Italian.

All Apache 2.0 licensed. Free for commercial use. No restrictions.

Performance:

- French: 97.97% F1 (top model)
- German: 97.61% F1 (top model)
- Italian: 97.28% F1 (top model)

All top-10 models per language exceed 96% F1

Coverage:

55+ PII entity types per language
Native ID formats: NSS (French), Sozialversicherungsnummer (German), Codice Fiscale (Italian)
Language-specific address, phone, and name patterns

Training Data:

French: 49,580 samples
German: 42,250 samples
Italian: 40,944 samples

Why Multilingual?

European healthcare operates in European languages. Clinical notes, patient records, and medical documents are generated in French, German, Italian, and other languages.

Effective de-identification requires:

- Native language understanding โ€” not translation
- Local ID format recognition โ€” each country has unique patterns
- Cultural context awareness โ€” names, addresses, and formats vary
- These models deliver production-ready accuracy without requiring data to leave your infrastructure or language.

HIPAA & GDPR Compliance
Built for US and European privacy regulations:

- On-premise deployment: Process data locally with zero external dependencies
- Data sovereignty: No API calls, no cloud services, no cross-border transfers
- Air-gapped capable: Deploy in fully isolated environments if required
- Regulatory-grade accuracy: Supporting Expert Determination standards
- HIPAA and GDPR compliance across languages, without compliance gaps.

Use Cases
- Hospital EHR systems: Automated patient record de-identification
- Clinical research: Multilingual dataset preparation for studies
- Insurance companies: Claims processing across

https://huggingface.co/collections/OpenMed/multilingual-pii-and-de-identification
  • 1 reply
ยท