|
--- |
|
language: |
|
- en |
|
tags: |
|
- Parallel Tacotron |
|
- Univnet |
|
datasets: |
|
- CMU Arctic |
|
--- |
|
|
|
# TTS Models |
|
|
|
Here you can find models compatible with |
|
[balacoon_tts](https://pypi.org/project/balacoon_tts/) python package. |
|
You can check interactive demo and models usage example in |
|
[balacoon/tts](https://huggingface.co/spaces/balacoon/tts) space. |
|
|
|
List of available models: |
|
|
|
- <mark>en_us_cmuarctic_pt_univenet.addon</mark> - en-US TTS trained on all 18 |
|
[CMU Arctic](http://festvox.org/cmu_arctic/) voices. This includes |
|
examples of absolutely dashing accents, with "slp" voice being my |
|
personal absolute favorite. Model consists of |
|
[Parallel Tacotron](https://arxiv.org/abs/2010.11439) |
|
and pre-trained [Univnet](https://github.com/mindslab-ai/univnet). |
|
Model produces 24khz audio, although original dataset is unfortunately |
|
16khz, so high frequencies are empty :( |
