SSAK contains helpers and tools to process data and train/infer ASR models.

Code for continual pretraining of LUCIE

LinShare - Secure File Sharing

The open-source alternative to Google Drive.

A multi-platform (Flutter) application for reading your emails, with your favorite devices, using the JMAP protocol!

A multi-platform (Flutter) application for connecting to Matrix - an open network for secure, decentralized communication, with your favorite devices.

Corpus of political debates : transcriptions and summaries

Welcome to OpenLLM-France 🇫🇷

Lists of conversational datasets

French instruction-following and chat models

Continual pretraining of foundation LLM using ⚡ Lightning Fabric

Glossaire des termes liés au LLM.

Page de préconfiguration de la communauté OpenLLM-France

Public product Roadmap

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

LinTO's NLP service: Extractive Summarization

LinTO Platform punctuation service.

LinTO's NLP core services

Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.

Open standard for machine learning interoperability

Duck-themed multi-user virtual spaces in WebVR. Built with A-Frame.

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Emails at the heart of your business logic!

(WIP) Development folder for the LinTO android client.

Transcription and annotation interface for recorded audio or video files

The SpeechBrain project aims to build a novel speech toolkit fully based on PyTorch. With SpeechBrain users can easily create speech processing systems, ranging from speech recognition (both HMM/DN…

Wake me up is a collaborative interface to make audio sample acquisition and validation.