Pantagruel: Unified Self-Supervised Encoders for French Text and Speech
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911537010049024 |
|---|---|
| author | Le, Phuong-Hang Pelloin, Valentin Chatelain, Arnault Bouziane, Maryem Ghennai, Mohammed Guan, Qianwen Milintsevich, Kirill Mdhaffar, Salima Mannion, Aidan Defauw, Nils Gu, Shuyue Audibert, Alexandre Dinarelli, Marco Estève, Yannick Goeuriot, Lorraine Lalande, Steffen Hervé, Nicolas Coavoux, Maximin Portet, François Ollion, Étienne Candito, Marie Peyrard, Maxime Rossato, Solange Lecouteux, Benjamin Nardy, Aurélie Sérasset, Gilles Segonne, Vincent Evain, Solène Fabre, Diandra Schwab, Didier |
| author_facet | Le, Phuong-Hang Pelloin, Valentin Chatelain, Arnault Bouziane, Maryem Ghennai, Mohammed Guan, Qianwen Milintsevich, Kirill Mdhaffar, Salima Mannion, Aidan Defauw, Nils Gu, Shuyue Audibert, Alexandre Dinarelli, Marco Estève, Yannick Goeuriot, Lorraine Lalande, Steffen Hervé, Nicolas Coavoux, Maximin Portet, François Ollion, Étienne Candito, Marie Peyrard, Maxime Rossato, Solange Lecouteux, Benjamin Nardy, Aurélie Sérasset, Gilles Segonne, Vincent Evain, Solène Fabre, Diandra Schwab, Didier |
| contents | We release Pantagruel models, a new family of self-supervised encoder models for French text and speech. Instead of predicting modality-tailored targets such as textual tokens or speech units, Pantagruel learns contextualized target representations in the feature space, allowing modality-specific encoders to capture linguistic and acoustic regularities more effectively. Separate models are pre-trained on large-scale French corpora, including Wikipedia, OSCAR and CroissantLLM for text, together with MultilingualLibriSpeech, LeBenchmark, and INA-100k for speech. INA-100k is a newly introduced 100,000-hour corpus of French audio derived from the archives of the Institut National de l'Audiovisuel (INA), the national repository of French radio and television broadcasts, providing highly diverse audio data. We evaluate Pantagruel across a broad range of downstream tasks spanning both modalities, including those from the standard French benchmarks such as FLUE or LeBenchmark. Across these tasks, Pantagruel models show competitive or superior performance compared to strong French baselines such as CamemBERT, FlauBERT, and LeBenchmark2.0, while maintaining a shared architecture that can seamlessly handle either speech or text inputs. These results confirm the effectiveness of feature-space self-supervised objectives for French representation learning and highlight Pantagruel as a robust foundation for multimodal speech-text understanding. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_05911 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Pantagruel: Unified Self-Supervised Encoders for French Text and Speech Le, Phuong-Hang Pelloin, Valentin Chatelain, Arnault Bouziane, Maryem Ghennai, Mohammed Guan, Qianwen Milintsevich, Kirill Mdhaffar, Salima Mannion, Aidan Defauw, Nils Gu, Shuyue Audibert, Alexandre Dinarelli, Marco Estève, Yannick Goeuriot, Lorraine Lalande, Steffen Hervé, Nicolas Coavoux, Maximin Portet, François Ollion, Étienne Candito, Marie Peyrard, Maxime Rossato, Solange Lecouteux, Benjamin Nardy, Aurélie Sérasset, Gilles Segonne, Vincent Evain, Solène Fabre, Diandra Schwab, Didier Computation and Language We release Pantagruel models, a new family of self-supervised encoder models for French text and speech. Instead of predicting modality-tailored targets such as textual tokens or speech units, Pantagruel learns contextualized target representations in the feature space, allowing modality-specific encoders to capture linguistic and acoustic regularities more effectively. Separate models are pre-trained on large-scale French corpora, including Wikipedia, OSCAR and CroissantLLM for text, together with MultilingualLibriSpeech, LeBenchmark, and INA-100k for speech. INA-100k is a newly introduced 100,000-hour corpus of French audio derived from the archives of the Institut National de l'Audiovisuel (INA), the national repository of French radio and television broadcasts, providing highly diverse audio data. We evaluate Pantagruel across a broad range of downstream tasks spanning both modalities, including those from the standard French benchmarks such as FLUE or LeBenchmark. Across these tasks, Pantagruel models show competitive or superior performance compared to strong French baselines such as CamemBERT, FlauBERT, and LeBenchmark2.0, while maintaining a shared architecture that can seamlessly handle either speech or text inputs. These results confirm the effectiveness of feature-space self-supervised objectives for French representation learning and highlight Pantagruel as a robust foundation for multimodal speech-text understanding. |
| title | Pantagruel: Unified Self-Supervised Encoders for French Text and Speech |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2601.05911 |