README.md

---
license: mit
base_model: openai/whisper-large-v3-turbo
base_model_relation: quantized
library_name: epure-runtime
pipeline_tag: automatic-speech-recognition
language:
  - en
tags:
  - exeaon
  - epure
  - compressed
  - quantized
  - whisper
  - asr
  - edge
  - cpu
---

# Exeaon1-Voice-0.8B

Speech recognition, compressed with E-PURE. Runs with the free
[`epure-runtime`](https://github.com/ExeaonLM/epure-runtime) and **stays
compressed in memory** — the dense weight is never assembled.

| | |
|---|---|
| Base model | [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) |
| Size on disk | **0.44 GB** (base 1.51 GB) |
| Compression | **3.43x** |
| Bits per weight | 4.22 (measured index entropy) |
| Compensated layers | 233 of 233 — none fell back to plain rounding |
| Format | `.ebin` |

## Quality

Word error rate, not perplexity: perplexity is meaningless for ASR and file
size proves nothing. Both models saw identical audio and decoded greedily, so
the only variable is the weights.

| | WER |
|---|---|
| whisper-large-v3-turbo | **5.20%** |
| **Exeaon1-Voice-0.8B** | **5.20%** |
| token disagreement | 0.12% |

**No measurable degradation.** The original's WER is reported alongside because
a compressed model can only be judged against what the model could do in the
first place — if the original errs on a clip, the compressed one repeating that
error is not damage we caused.

Sample, same clip, both models:

```
ref   MISTER QUILTER IS THE APOSTLE OF THE MIDDLE CLASSES AND WE ARE GLAD TO
      WELCOME HIS GOSPEL
base  Mr. Quilter is the apostle of the middle classes, and we are glad to
      welcome his gospel.
ours  Mr. Quilter is the apostle of the middle classes, and we are glad to
      welcome his gospel.
```

## Why audio compresses this well

Whisper is an encoder-decoder: 32 encoder layers carry most of the parameters
and 4 decoder layers the rest. Both stacks are compensated — compressing only
the larger one would leave an eighth of the model on plain rounding.

Calibration uses real speech. The encoder's activations are dominated by
mel-spectrogram structure that random input does not reproduce, so noise
calibration would compensate against statistics the model never sees.

Convolutional weights in the audio frontend are left dense: `conv1.weight` is
`[1280, 128, 3]`, a kernel of 3 against a group size of 128, which cannot be
usefully quantized and is a negligible share of parameters.

## Usage

```bash
pip install epure-runtime
```

```python
from epure import load

model, proc = load("Exeaon/Exeaon1-Voice-0.8B")
```

The container bundles `preprocessor_config.json`, so the feature extractor
builds without fetching anything from the base repository.

## Limitations

- Evaluated on read English speech (LibriSpeech-style). Accented, noisy,
  overlapping or non-English audio is not covered by the number above.
- WER was measured on a small clip set; treat 5.20% as an indicative figure on
  clean speech, not a benchmark-suite result.
- Inherits every limitation and bias of the base model.
- Not evaluated for safety-critical, medical or legal transcription.

## Licence and attribution

Derived from
[openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo),
released under the MIT licence, which permits redistribution of modified
versions. The base repository ships no `LICENSE` file; the licence is declared
in its model card metadata and is reproduced in this repository.

**Ours:** the compression method, calibration, packaging, runtime.
**Not ours:** the pretrained knowledge, which comes from OpenAI. This model is
not endorsed by or affiliated with OpenAI.

## Citation

```bibtex
@misc{exeaon2026,
  title  = {Exeaon: compressed models that run, and train, without
            decompressing},
  author = {Akpalu, Elliot Elikplim},
  year   = {2026},
  publisher = {Zenux Plimver Technologies LTD},
  url    = {https://huggingface.co/Exeaon}
}
```

---

<sub>Zenux Plimver Technologies LTD, Ghana</sub>