---
license: mit
library_name: vokra
tags:
  - vokra
  - gguf
---

# pyannote-segmentation-3.0 (Vokra GGUF)

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 |
|---|---|---|
| `pyannote-seg.gguf` | 5.6 MB | `22ff05fddf19e69c8d9aac8daa6d99014e6718bcd8d8c527d26da677d00c63f1` |

## Usage

```bash
# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o pyannote-seg.gguf \
  https://huggingface.co/vokra/pyannote-segmentation-3.0/resolve/main/pyannote-seg.gguf
```

```bash
vokra-cli run --model pyannote-seg.gguf --input input.wav
```

## Provenance

| Field | Value |
|---|---|
| Architecture | `pyannote-segmentation` |
| Tensors | 54 |
| Upstream source | pyannote/segmentation-3.0 |
| Upstream licence | `mit` |
| Licence class | `permissive` |
| Registry model id | `pyannote-segmentation-3.0` |
| 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 **mit**, unchanged from upstream. Conversion does not alter the licence, and your obligations run to the upstream author.

## Verifying this file

```bash
shasum -a 256 pyannote-seg.gguf
# expect: 22ff05fddf19e69c8d9aac8daa6d99014e6718bcd8d8c527d26da677d00c63f1
```