huggingPartyParis

community

https://partiful.com/e/oWOMGoPxB5D37qw5F8yN

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

prithv1 authored a paper 2 days ago

Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning

sayakpaul authored a paper 9 days ago

SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation

phedman authored a paper 6 months ago

EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis

View all activity

HuggingPartyParis's activity

Aurelien-Morgan

posted an update 5 months ago

Post

503

I just shipped retrain-pipelines 0.1.1 today. The doc is also pimped compared to previous release. That was clearly not mature then.
I'll have to focus on another project for the next couple weeks but, anyone feel free to open issues on the GitHub repo and discuss any interest you'd have there if you will (please?) !
In the meantime, you may enjoy retrying this :
https://huggingface.co/blog/Aurelien-Morgan/stateful-metaflow-on-colab

Aurelien-Morgan

posted an update 5 months ago

Post

560

I just published the first article in a pair. I could make it a longer tailed series, in case you liked em. This one dives into self-hosting Metaflow without needing S3, illustrated with a version tailored for Google Colab.
find it @ https://huggingface.co/blog/Aurelien-Morgan/stateful-metaflow-on-colab

2 replies

devendrachaplot

authored a paper 5 months ago

Pixtral 12B

Paper • 2410.07073 • Published Oct 9, 2024 • 64

Simontwice

authored a paper 5 months ago

Pixtral 12B

Paper • 2410.07073 • Published Oct 9, 2024 • 64

ymxlzgy

authored 2 papers 6 months ago

IPCC-TP: Utilizing Incremental Pearson Correlation Coefficient for Joint Multi-Agent Trajectory Prediction

Paper • 2303.00575 • Published Mar 1, 2023

EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusion

Paper • 2405.00915 • Published May 2, 2024

lmathur

authored a paper 9 months ago

HEMM: Holistic Evaluation of Multimodal Foundation Models

Paper • 2407.03418 • Published Jul 3, 2024 • 12

martin-r-oswald

authored a paper 9 months ago

An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels

Paper • 2406.09415 • Published Jun 13, 2024 • 51

WalidBouss

authored a paper 10 months ago

LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity

Paper • 2404.03214 • Published Apr 4, 2024 • 2

sa8

posted an update 10 months ago

Post

1058

I've just published the first part of a series on open problems in decentralized AI infrastructure .

This one focuses on verifiable computations, would love some feedback from the HF community!

https://link.medium.com/5YYUnNpcEJb

1 reply

cetosignis

authored a paper 11 months ago

Better & Faster Large Language Models via Multi-token Prediction

Paper • 2404.19737 • Published Apr 30, 2024 • 77

malper

authored a paper 11 months ago

HaLo-NeRF: Learning Geometry-Guided Semantics for Exploring Unconstrained Photo Collections

Paper • 2404.16845 • Published Feb 14, 2024 • 7

amonszpart

authored 2 papers 11 months ago

Removing Objects From Neural Radiance Fields

Paper • 2212.11966 • Published Dec 22, 2022

Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer

Paper • 2404.14351 • Published Apr 22, 2024 • 6

ylacombe

posted an update 12 months ago

Post

7290

Yesterday, we released Parler-TTS and Data-Speech, fully open-source reproduction of work from the paper: Natural language guidance of high-fidelity text-to-speech with synthetic annotations (2402.01912)

Parler-TTS is a lightweight text-to-speech (TTS) model that can generate high-quality, natural sounding speech in the style of a given speaker (gender, pitch, speaking style, etc).

https://huggingface.co/collections/parler-tts/parler-tts-fully-open-source-high-quality-tts-models-66164ad285ba03e8ffde214c

Parler-TTS Mini v0.1, is the first iteration Parler-TTS model trained using 10k hours of narrated audiobooks. It generates high-quality speech with features that can be controlled using a simple text prompt (e.g. gender, background noise, speaking rate, pitch and reverberation).

To improve the prosody and naturalness of the speech further, we're scaling up the amount of training data to 50k hours of speech. The v1 release of the model will be trained on this data, as well as inference optimisations, such as flash attention and torch compile.

parler-tts/parler_tts_mini_v0.1

Data-Speech can be used for annotating speech characteristics in a large-scale setting.

parler-tts/open-source-speech-datasets-annotated-using-data-speech-661648ffa0d3d76bfa23d534

This work is both scalable and easily modifiable and will hopefully help the TTS research community explore new ways of conditionning speech synthesis.

All of the datasets, pre-processing, training code and weights are released publicly under permissive license, enabling the community to build on our work and develop their own powerful TTS models.