KyutaiHibiki
Hibiki 2B
Hibiki 2B translates French speech into English speech and aligned text as the speaker talks. It aims to preserve the source voice while adapting when enough speech has arrived for a translation.
Research release
Voice fidelity and translation can trade off
The release was trained on recordings up to 120 seconds. Increasing classifier-free guidance can preserve the voice more closely but can reduce translation quality. MLX, Rust and quantized releases are formats of the corresponding model.hibiki-2b-pytorch-bf16: Kyutai model card
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | kyutai/hibiki-2b-mlx-bf16kyutai/hibiki-2b-pytorch-bf16kyutai/hibiki-2b-rs-bf16 |
| Reported parameter count | 2.7 billion parameters; the repository name is a shorter family label.hibiki-2b-pytorch-bf16: Kyutai model card |
| Audio rate | 2.2 kilobits per second at 12.5 frames per second.hibiki-2b-pytorch-bf16: Kyutai model card |
| License | CC BY 4.0.hibiki-2b-pytorch-bf16: Kyutai model card |
Related models
- Hibiki Zero 3B
Kyutai ยท Hibiki
A speech model that translates French, Spanish, Portuguese and German into English using sentence-aligned training.
Launch date not confirmedResearch releaseDownloadable