mimi / README.md
ayousanz's picture
Upload folder using huggingface_hub
13e99bb verified
|
Raw
History Blame Contribute Delete
2.19 kB
---
license: cc-by-4.0
library_name: vokra
tags:
- vokra
- gguf
- neural-audio-codec
---
# mimi (Vokra GGUF)
Neural audio codec model, converted to the Vokra GGUF format for [Vokra](https://github.com/ayutaz/vokra), a zero-dependency speech-AI inference runtime.
**This is a conversion, not a new model.** The weights are the upstream ones; Vokra re-packages them so its runtime can memory-map them directly. Credit for the model belongs upstream — see *Source* below.
## Files
| File | Size | SHA-256 |
|---|---|---|
| `mimi.gguf` | 864.4 MB | `8fc9b2113a0dfe96209e5380b0e64acc89c937e3fe1ecb98703ba1c75a921bb0` |
## Usage
```bash
# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o mimi.gguf \
https://huggingface.co/vokra/mimi/resolve/main/mimi.gguf
```
```bash
# This artifact is consumed by another engine rather than run
# standalone — see the Vokra docs for the CODEC pipeline.
```
## Provenance
| Field | Value |
|---|---|
| Architecture | `mimi` |
| Tensors | 603 |
| Upstream source | kyutai/moshiko-pytorch-bf16 tokenizer-e351c8d8-checkpoint125.safetensors |
| Upstream licence | `CC-BY-4.0` |
| Licence class | `attribution-required` |
| Registry model id | `mimi` |
| Vokra GGUF schema | 1 |
| Converted by | vokra-core 0.1.0-alpha.0 |
Every row above is read out of this file's own `vokra.*` metadata, so the card cannot claim something the artifact does not carry.
## Licence
The weights are distributed under **CC-BY-4.0**, unchanged from upstream. Conversion does not alter the licence, and your obligations run to the upstream author.
### Attribution required
> This application uses the Mimi neural audio codec by Kyutai. Mimi weights are licensed under CC-BY 4.0 (attribution required; commercial use permitted). Copyright (c) Kyutai / Moshi authors. Source: https://github.com/kyutai-labs/moshi
This licence obliges you to display the attribution above when you ship something built on these weights. Vokra surfaces it at runtime via `vokra_model_attribution` (C ABI) and a CLI banner.
## Verifying this file
```bash
shasum -a 256 mimi.gguf
# expect: 8fc9b2113a0dfe96209e5380b0e64acc89c937e3fe1ecb98703ba1c75a921bb0
```