Soynade Research

The moon shines for everyone.

[Soynade Research @soynade]

After Wolof, Fula will soon be supported by Oolel-Voices, our open-source speech generation model.

[Soynade Research @soynade]

Release 3 of the Soynade Open Source Month.

Oolel-Voices: a speech generation model supporting voice cloning with expressive, modular control over tone and pace, making it suitable for content creation.

Try it now: https://t.co/vJltnEKH6V
Model: https://t.co/3O1egcmFt4

[Soynade Research @soynade]

We are releasing Oolel-Corrector, a new model in the Oolel family trained to fix non-standard Wolof orthography as commonly written on social media.

The model is available on Hugging Face.

https://t.co/PVKNy43TnA

[Soynade Research @soynade]

We're releasing a dataset of non-standard Wolof orthography. The goal is to help models understand Wolof as it's actually written online, not just as it should be.

Dataset: https://t.co/KtP7O00aYB

[Soynade Research @soynade]

We're releasing a dataset of non-standard Wolof orthography. The goal is to help models understand Wolof as it's actually written online, not just as it should be.

Dataset: https://t.co/KtP7O00aYB

[Soynade Research @soynade]

We're releasing a dataset of non-standard Wolof orthography. The goal is to help models understand Wolof as it's actually written online, not just as it should be.

Dataset: https://t.co/KtP7O00aYB

[Soynade Research @soynade]

Oolel-Embed est efficace grâce aux représentations Matryoshka, permettant de représenter l'information dans des espaces vectoriels très petits.

Voyez Oolel-Embed en action:

[Soynade Research @soynade]

4e publication du mois de l'open-source de Soynade.

Oolel-Embed: un modèle permettant de récupérer des documents directement à partir de la parole, sans passer par des étapes intermédiaires coûteuses de reconnaissance vocale et de traduction.

Model: https://t.co/sDTZoT2iV7

[Soynade Research @soynade]

Release 3 of the Soynade Open Source Month.

Oolel-Voices: a speech generation model supporting voice cloning with expressive, modular control over tone and pace, making it suitable for content creation.

Try it now: https://t.co/vJltnEKH6V
Model: https://t.co/3O1egcmFt4

[Soynade Research @soynade]

Read our paper for more details.
https://t.co/sLkcsqNQ3F

[Soynade Research @soynade]

Release 2 of the Soynade Open Source Month.

A small foundational speech representation model for Wolof, continued pretrained from Meta/HuBERT on 860 hours of Wolof speech. This improves the ASR performance using only unlabeled speech data.
https://t.co/vQizR2galx

[Soynade Research @soynade]

Continued pre-training allows us to be more compute-optimal than Orange's model while significantly outperforming the base Meta/HuBERT-Base model.

We release the ASR fine-tuned model along with 100 hours of clean Wolof ASR data.

Models and dataset here:
https://t.co/dlHyl8Q20o

[Soynade Research @soynade]

- AfVoices-Translated: https://t.co/jOiA3TZLnr

- FineWeb-Wolof-50k: https://t.co/ThDU99H57L

- Oolel-Translator: https://t.co/Eyh4tqk3Em

[Soynade Research @soynade]

Today we kick off Soynade's Open Source Month, four weeks of releasing models, datasets, and tools for African languages.

Learn more: https://t.co/6xv2yMrluu

The first release is live:
→ AfVoices-Translated: +200k Bambara-English speech translation dataset with acoustic tags.

[Soynade Research @soynade]

Frontier technology, research, and data should circulate, not sit behind closed doors. Anyone should be able to audit it, extend it, and build on it.

[Soynade Research @soynade]

Ce qui permettra d'avoir des capacité multimodales pour les langues africaines à moindre coût 💸

Stay tuned! On a plein de modèles ouverts qui arrivent.

[Soynade Research @soynade]

Oolel peut voir des images et vidéos : un vision LLM ouvert pour le wolof.
Et il n’a été entraîné sur aucune donnée visuelle en wolof !
On explore des pistes de recherche pour transférer les capacités multimodales d’une langue à une autre, sans entraînement multimodal direct.

[Soynade Research @soynade]

It has been optimized for essential tasks like natural text generation in Wolof and English, translation, and RAG capabilities, while maintaining a compact size.

[Soynade Research @soynade]

𝐎𝐨𝐥𝐞𝐥-𝐒𝐦𝐚𝐥𝐥-1𝐁: On-device AI for Wolof with a Lightweight Language Model 

🚀 Meet Oolel Small, the lighter version of the Wolof LLM Oolel - bringing on-device AI to Wolof speakers. You can run it locally without any internet connectivity

[Soynade Research @soynade]

En attendant, vous pouvez d'ores et déjà combiner ces deux technologies. C'est la beauté de l'open source - des innovations qui se complètent pour faire avancer les technologies pour les langues sous-représentées.

[Soynade Research @soynade]

Petite expérience intéressante que vous pouvez reproduire : générer du texte avec notre LLM 𝐎𝐨𝐥𝐞𝐥 et le vocaliser à l’aide du modèle Text-to-Speech de @galsenai.

[Soynade Research @soynade]

La combinaison de ces deux modèles open source ouvre la voie à de nombreux cas d'usage : création de contenus audio, assistants vocaux, etc. Les prochaines versions d'Oolel intégreront directement des capacités vocales.