Toad HF Inference Explorers

community

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

emanuelaboros authored a paper 20 days ago

Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking

emanuelaboros authored a paper 20 days ago

When Superpixels Fail on Documents: A Study of Segmentation for LIME Explanations

emanuelaboros authored a paper 26 days ago

ICDAR 2026 HIPE-OCRepair Competition on LLM-Assisted OCR Post-Correction for Historical Documents

View all activity

Nymbo

posted an update 8 days ago

Post

3,673

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

emanuelaboros

authored 2 papers 20 days ago

Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking

Paper • 2609.07379 • Published Sep 10 • 1

When Superpixels Fail on Documents: A Study of Segmentation for LIME Explanations

Paper • 2609.07462 • Published Sep 7

emanuelaboros

authored 2 papers 26 days ago

ICDAR 2026 HIPE-OCRepair Competition on LLM-Assisted OCR Post-Correction for Historical Documents

Paper • 2607.08143 • Published Jul 9 • 1

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments

Paper • 2509.14233 • Published Sep 17, 2025 • 25

mrfakename

posted an update about 1 month ago

Post

2,185

We’ve been working with LAION on a voice acting arena. You listen to two models doing the same scene and compare how well they pull it off.

It’s ready to try now - would love to hear what you think 🙂

TTS-AGI/voice-acting-arena

leonardlin

posted an update 2 months ago

Post

247

I've trained an uploaded a proper MTP head for Ornith 1.5:
- head only: shisa-ai/Ornith-1.5-35B-A3B-MTP-ONLY
- full BF16: shisa-ai/Ornith-1.5-35B-A3B-MTP
- FP8: shisa-ai/Ornith-1.5-35B-A3B-MTP-FP8

evalstate

posted an update 2 months ago

Post

2,148

Hugging Face MCP Server v0.4.9
~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Attach images from hf_fs tool.

Nymbo

posted an update 3 months ago

Post

2,564

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 — issues and PRs welcome.

Nymbo

posted an update 3 months ago

Post

6,195

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

evalstate

posted an update 4 months ago

Post

1,453

Hugging Face MCP Server v0.3.29
~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Included "papers" in the new hf_fs tool. Includes listing of trending/daily.

This is a new tool under observation - disable the "Paper Semantic Search" tool for best results.

hf://papers/
├── README.md
├── daily/
│   ├── latest
│   └── YYYY/
│       └── MM/
│           └── DD/
├── trending/
└── ARXIV_ID/
    ├── metadata.json
    ├── paper.md
    ├── models/
    ├── datasets/
    └── spaces/

emanuelaboros

authored a paper 4 months ago

A Study of Temporal Fusion Strategies for Named Entity Recognition in Historical Texts

Paper • 2606.27881 • Published Jun 26 • 1

evalstate

posted an update 5 months ago

Post

3,493

Hugging Face MCP Server v0.3.17
~~~~~~~~~~~~~~~~~~~~~~~~~~~~

SEP-2640 "Skills Over MCP" support added (early access)

3 replies

evalstate

posted an update 5 months ago

Post

381

Hugging Face MCP Server v0.3.13
~~~~~~~~~~~~~~~~~~~~~~~~~~~~

The hf_jobs tool allows mounting of volumes with hf:// URI's and some additional notes about use for data analysis.

Tonic

posted an update 5 months ago

Post

3,528

🙋🏻‍♂️ 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 🛰️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 📡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

evalstate

posted an update 6 months ago

Post

2,247

Hugging Face MCP Server v0.3.12
~~~~~~~~~~~~~~~~~~~~~~~~~~~~

The hub_repo_details tool now enables Dataset inspection (view splits, sample rows).

evalstate

posted an update 6 months ago

Post

337

Hugging Face MCP Server v0.3.10
~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Reverted mcp bucket in favour of upcoming MCP App integration.

Tonic

posted an update 6 months ago

Post

4,518

🙋🏻‍♂️ 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 ! 🚀

2 replies

evalstate

posted an update 6 months ago

Post

1,007

Hugging Face MCP Server v0.3.9
~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Users with a bucket named mcp will get an additional list_files tool that returns the public URL of contained files. This is primarily intended for use with Gradio Spaces that need URLs as inputs.

Tonic

posted an update 6 months ago

Post

3,763

🙋🏻‍♂️ 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 🚀

AI & ML interests

Recent Activity

Team members 153

toad-hf-inference-explorers's activity