|
|
--- |
|
|
license: cc-by-4.0 |
|
|
language: |
|
|
- en |
|
|
base_model: |
|
|
- rhasspy/piper-voices |
|
|
pipeline_tag: text-to-speech |
|
|
--- |
|
|
# 🗣️ Colin Voice – Fine-tuned Piper TTS (en_GB) |
|
|
|
|
|
This repository hosts a fine-tuned [Piper](https://github.com/rhasspy/piper) text-to-speech model based on the **English (GB)** voice from [`rhasspy/piper-checkpoints`](https://huggingface.co/rhasspy/piper-checkpoints). |
|
|
It was adapted using ~300 high-quality recordings of my own voice to achieve a more **natural, expressive**, and **personally identifiable** British English tone. |
|
|
|
|
|
--- |
|
|
|
|
|
## Overview |
|
|
|
|
|
| Feature | Description | |
|
|
|----------|--------------| |
|
|
| **Base Model** | [`rhasspy/piper-checkpoints`](https://huggingface.co/rhasspy/piper-checkpoints) | |
|
|
| **Language / Accent** | English (Great Britain) | |
|
|
| **Training Data** | 300 clean voice samples (~30 minutes total) | |
|
|
| **Format** | ONNX + JSON config | |
|
|
| **License** | CC BY-NC-SA 4.0 *(for personal/non-commercial use only)* | |
|
|
|
|
|
--- |
|
|
|
|
|
## Notes |
|
|
|
|
|
- This model reproduces my own voice and is not intended for impersonation or commercial use. |
|
|
- Please credit Colin Salvatore Nardo and link back to this repository when sharing generated samples. |
