---
license: gpl-3.0
tags:
  - onnx
  - allosaurus
  - phoneme-recognition
  - speech
  - lipsync
library_name: onnxruntime
---

# Uni2005 ONNX

An ONNX export of the **Uni2005** universal phoneme-recognition acoustic model
from [Allosaurus](https://github.com/xinjli/allosaurus). It is published by
KitsuMate as a separately downloadable runtime model for
`ai.kitsumate.onnx.lipsync`; it is not bundled in the Unity package.

## Contents

| File | Purpose | SHA-256 |
| --- | --- | --- |
| `uni2005.onnx` | Float32 ONNX acoustic model | `517b07ccd197b8acb2c18c3f6ca19e1e8fd489b81853e386720917e01d43de1e` |
| `phone.txt` | Universal phone inventory | `bfe6cd8566c2c3a158da6134ba0d067d179123f6adfcac8ea9c7e44671423848` |
| `vocab.json` | CTC token-to-phone mapping | `8dbf53951b7ac3379b4f6dcfdb9f6b659f588fac7d4fa04c1395876f0462a338` |

`checksums.sha256` is the machine-readable form of these hashes.

## Model contract

- Input: `mfcc`, `float32`, shape `[batch, time, 120]` (dynamic batch/time).
- Output: `logits`, `float32`, shape `[batch, time, 230]`.
- Audio preprocessing: 8 kHz mono audio; 25 ms window; 10 ms hop; 40 MFCC
  coefficients with speaker CMVN, three-frame context windows, and a factor-3
  subsample. The model does not perform resampling or MFCC extraction.
- Decode the output with CTC using `vocab.json`.

The repository currently publishes the full-precision export only. It has not
been qualified for every ONNX runtime or Unity AI Inference operator set.

## Provenance and licence

The model is derived from the `uni2005` model in
[xinjli/allosaurus](https://github.com/xinjli/allosaurus), recorded here at
commit `d9f1adaf47d3b3765b41f4177da62a051516d636`. See [NOTICE](NOTICE) for
attribution and the included [GPL-3.0 licence](LICENSE) for terms.

KitsuMate does not claim authorship of the original Allosaurus model and does
not imply endorsement by its authors. The source model and these redistributed
artifacts are covered by GPL-3.0 as confirmed for this publication.

## Use with KitsuMate ONNX

Pin a Hugging Face commit revision and verify the published SHA-256 before
placing the three runtime files in your application's model cache. Do not add
them to a UPM package archive.