pseudolab (Pseudo Lab)

posted an update 9 days ago

Post

142

Surogate Speech is out 🐇 small open speech models for agents, the speech side of Surogate.

First language shipped is Romanian, and the numbers came out better than I expected: 5.69% WER on FLEURS with a 116M model. Canary 1B gets 5.95% on the same clips, Whisper large-v3 8.42%. Leaderboard runner, one RTX 5090.

What's in it:

🎧 jackrabbit-110m-ro: speech recognition, 2,500× real time on one GPU
⚡ jackrabbit-110m-ro-streaming: live, final text about 0.7 s after you stop talking
🗣️ amami-357m-ro: TTS with three voices, runs on a CPU

Serving is one line with our engine: surogate serve --stt surogate/jackrabbit-110m-ro

Transcripts for every clip are public if you want to rescore it.

surogate/surogate-speech-6ab680eb84c7ff75fb73ad5a
https://github.com/invergent-ai/surogate-speech

Nymbo

posted an update about 2 months ago

Post

2394

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 2 months ago

Post

6102

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

·

cppraii

updated a model 2 months ago

pseudolab/GR00T-N1.7-3B-OMX-PickupDolls-2Cam

Robotics • 3B • Updated Jul 22 • 14 • 1

cppraii

published a model 2 months ago

pseudolab/GR00T-N1.7-3B-OMX-PickupDolls-2Cam

Robotics • 3B • Updated Jul 22 • 14 • 1

juyoungml

authored a paper 3 months ago

On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists

Paper • 2605.20668 • Published May 20 • 14

cppraii

updated a model 3 months ago

pseudolab/GR00T-N1.7-3B-OMX-PickupDolls

Robotics • 3B • Updated Jul 14 • 9 • 1

cppraii

published a model 3 months ago

pseudolab/GR00T-N1.7-3B-OMX-PickupDolls

Robotics • 3B • Updated Jul 14 • 9 • 1

LeoKimDowny

updated a dataset 3 months ago

pseudolab/omx_f_PickUpDollWith2Cam

omx_f • Updated Jul 9 • 94 episodes • 396 • 1

cetusian

posted an update 3 months ago

Post

148

most labs won't bother teaching a small model to write and think in real romanian. no invented words, no english leaking in mid-sentence, diacritics intact.

we did.

surogate 3.5 is out. 2B and 4B, apache 2.0. invented word-forms cut from 4 per 1k down to ~1.5, and it reasons in the language you prompt it in, every time.

intelligence should speak your language too.

the models:

surogate/Surogate-3.5-4B

surogate/Surogate-3.5-2B

kinam0252

submitted a paper to Daily Papers 3 months ago

Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement

Paper • 2606.18953 • Published Jun 17 • 8

LeoKimDowny

published a dataset 3 months ago

pseudolab/omx_f_PickUpDollWith2Cam

omx_f • Updated Jul 9 • 94 episodes • 396 • 1

LeoKimDowny

updated a dataset 3 months ago

pseudolab/omx_f_PickUpDoll

omx_f • Updated Jun 26 • 85 episodes • 198

LeoKimDowny

published a dataset 3 months ago

pseudolab/omx_f_PickUpDoll

omx_f • Updated Jun 26 • 85 episodes • 198

yunihg

updated a dataset 4 months ago

pseudolab/omx_f_pick_doll

omx_f • Updated Jun 18 • 3 episodes • 39

yunihg

published a dataset 4 months ago

pseudolab/omx_f_pick_doll

omx_f • Updated Jun 18 • 3 episodes • 39

Tonic

posted an update 5 months ago

Post

3426

🙋🏻‍♂️ 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

2 replies

·

cppraii

published a dataset 5 months ago

pseudolab/omx-pick-place-dataset

Updated May 12 • 9

woojun-jung

authored a paper 5 months ago

QEVA: A Reference-Free Evaluation Metric for Narrative Video Summarization with Multimodal Question Answering

Paper • 2604.24052 • Published Apr 27

Tonic

posted an update 5 months ago

Post

4504

🙋🏻‍♂️ 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

·

AI & ML interests

Team members 67

pseudolab's activity