| File | Size | SHA-256 |
|---|---|---|
model.gguf | 4991.8 MB | d25302da6650309c094d0cbf10cfecfb507c31408b820304bda0c3195482f990 |
1# Download (any HTTP client works — the file is a plain GGUF)
2curl -L -o model.gguf \
3 https://huggingface.co/vokra/kyutai-stt-2.6b-en/resolve/main/model.ggufvokra-cli run --model model.gguf --input input.wav| Field | Value |
|---|---|
| Architecture | kyutai-stt |
| Tensors | 323 |
| Upstream source | https://huggingface.co/kyutai/stt-2.6b-en |
| Upstream licence | CC-BY-4.0 |
| Licence class | attribution-required |
| Registry model id | kyutai/stt-2.6b-en |
| 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 STT-2.6B-EN model (decoder-only English streaming ASR over Mimi audio tokens). Model weights are licensed under CC-BY 4.0 (attribution required; commercial use permitted). Copyright (c) Kyutai. Source: https://github.com/kyutai-labs/delayed-streams-modeling / https://huggingface.co/kyutai/stt-2.6b-en
vokra_model_attribution (C ABI) and a CLI banner.1shasum -a 256 model.gguf
2# expect: d25302da6650309c094d0cbf10cfecfb507c31408b820304bda0c3195482f990