| File | Size | SHA-256 |
|---|---|---|
hibiki-2b.gguf | 5316.5 MB | 62e70efbb54a612f51e3d7d35c9d901806331b642474d6e0857a73252aaf8934 |
1# Download (any HTTP client works — the file is a plain GGUF)
2curl -L -o hibiki-2b.gguf \
3 https://huggingface.co/vokra/hibiki-2b/resolve/main/hibiki-2b.ggufvokra-cli run --model hibiki-2b.gguf --input input.wav| Field | Value |
|---|---|
| Architecture | hibiki |
| Tensors | 327 |
| Upstream source | kyutai/hibiki-2b-pytorch-bf16 (simultaneous FR↔EN S2S translation, cc-by-4.0) |
| Upstream licence | cc-by-4.0 |
| Licence class | attribution-required |
| Registry model id | hibiki-2b |
| Vokra GGUF schema | 1 |
| Converted by | vokra-core 0.1.0-alpha.0 |
vokra.* metadata, so the card cannot claim something the artifact does not carry.This application uses the Kyutai Hibiki-2B model (simultaneous speech-to-speech translation, Helium + Mimi codec). Model weights are licensed under CC-BY 4.0 (attribution required; commercial use permitted). Copyright (c) Kyutai. Source: https://huggingface.co/kyutai/hibiki-2b-pytorch-bf16
vokra_model_attribution (C ABI) and a CLI banner.1shasum -a 256 hibiki-2b.gguf
2# expect: 62e70efbb54a612f51e3d7d35c9d901806331b642474d6e0857a73252aaf8934