@soynade profile picture
Soynade Research @soynade

The moon shines for everyone. soynade.ai

Joined November 2024
  • Tweets 22
  • Following 0
  • Followers 132
12 Photos and videos
After Wolof, Fula will soon be supported by Oolel-Voices, our open-source speech generation model.
0:30
Soynade Research@soynade
Mar 12
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: huggingface.co/spaces/soynad… Model: huggingface.co/soynade-resea…
0:26
4
4
582
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. huggingface.co/soynade-resea…

soynade-research/Oolel-Corrector · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

huggingface.co
Soynade Research@soynade
Mar 31
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: huggingface.co/datasets/soyn…
3
2
351
Soynade Research retweeted
Soynade Research@soynade
Mar 31
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: huggingface.co/datasets/soyn…

soynade-research/Wolof-Non-Standard-Orthography · Datasets at Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

huggingface.co
1
24
46
11,191
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: huggingface.co/soynade-resea…
0:27
2
19
38
6,771
Oolel-Embed est efficace grâce aux représentations Matryoshka, permettant de représenter l'information dans des espaces vectoriels très petits. Voyez Oolel-Embed en action:
0:40
2
8
1,283
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: huggingface.co/spaces/soynad… Model: huggingface.co/soynade-resea…
0:26
1
21
44
13,464
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. huggingface.co/soynade-resea…
1
13
24
2,372
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: huggingface.co/collections/s…
1
4
3
795
Read our paper for more details. arxiv.org/pdf/2509.15362
161
Today we kick off Soynade's Open Source Month, four weeks of releasing models, datasets, and tools for African languages. Learn more: soynade.ai/research/soynade-… The first release is live: → AfVoices-Translated: 200k Bambara-English speech translation dataset with acoustic tags.
0:10
1
5
5
983
more replies
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.
1
100
- AfVoices-Translated: huggingface.co/datasets/soyn… - FineWeb-Wolof-50k: huggingface.co/datasets/soyn… - Oolel-Translator: github.com/soynade-research/…

soynade-research/Bambara-Speech-Translation-Data · Datasets at Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

huggingface.co
1
94
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.
0:14
1
4
6
267
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.
2
2
145
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
0:50
1
12
13
2,899
It has been optimized for essential tasks like natural text generation in Wolof and English, translation, and RAG capabilities, while maintaining a compact size.
1
1
1
193
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.
0:27
1
1
1
191
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.
1
113
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.
1
1
110
Load more