---
license: mit
tags:
  - tts
  - text-to-speech
  - piper
  - vits
  - gguf
  - crispasr
base_model: rhasspy/piper-voices
pipeline_tag: text-to-speech
language:
  - en
---

# Piper TTS (en_US lessac medium) — GGUF

Native C++ GGUF conversion of the [Piper](https://github.com/rhasspy/piper) VITS voice `en_US-lessac-medium` for use with [CrispASR](https://github.com/CrispStrobe/CrispASR).

## Files

| File | Size | Description |
|------|------|-------------|
| `piper-en_US-lessac-medium-f16.gguf` | 30 MB | F16 weights (full model) |

Piper models are small enough that quantization provides no meaningful savings. F16 is the only format.

## Usage with CrispASR

```bash
./build/bin/crispasr --backend piper \
    -m piper-en_US-lessac-medium-f16.gguf \
    --tts "Hello, how are you today?" \
    --tts-output hello.wav
```

Phonemization uses espeak-ng (must be installed: `apt install espeak-ng`).

## Architecture

- **VITS** (Conditional Variational Autoencoder with Adversarial Learning)
- **Text encoder**: 6-layer relative-position transformer (192-d, 2 heads)
- **Duration predictor**: Stochastic Duration Predictor with rational-quadratic spline flows
- **Flow**: 4 affine coupling blocks with WaveNet conditioning
- **Decoder**: HiFi-GAN (3 upsample stages, 9 MRF resblocks)
- **Output**: 22.05 kHz mono PCM
- **License**: MIT

## Conversion

```bash
python models/convert-piper-to-gguf.py \
    --onnx en_US-lessac-medium.onnx \
    --output piper-en_US-lessac-medium-f16.gguf
```

## Provenance and EU AI Act Art. 53 note

- **Upstream model:** [rhasspy/piper-voices](https://huggingface.co/rhasspy/piper-voices) — published by `rhasspy`.
- **Upstream licence:** `mit`. This repository redistributes under the same terms; it grants no rights the upstream licence does not.
- **What was done here:** format conversion and/or quantisation only (GGUF). No training, no fine-tuning, no merging, no distillation, no change to architecture, vocabulary or capability. Only the numeric representation of the upstream weights differs.
- **Training data:** documented — where it is documented at all — by the upstream provider; see the upstream model card. No training data was used, added or selected by this repository. No training-content summary was found on the upstream model card at the time of writing; that documentation gap is upstream's and is not filled here.
- **Provider status:** under Regulation (EU) 2024/1689 the upstream authors remain the provider of this model. Converting the serialisation format does not make this repository the provider of a new general-purpose AI model, and no such claim is made. Questions about training content, copyright policy or model capability belong upstream.