README.md

metadata

language:
  - en
tags:
  - Parallel Tacotron
  - Univnet
  - Text-to-Speech
datasets:
  - CMU Arctic
  - Hi-Fi

TTS Models

Here you can find models compatible with balacoon_tts python package. You can check interactive demo and models usage example in balacoon/tts space.

List of available models:

• en_us_cmuarctic_pt_univenet.addon - en-US TTS trained on all 18 CMU Arctic voices.
• en_us_hifi92_pt_univenet.addon - en-US TTS trained on a single clean speaker(92) from Hi-Fi dataset.

Model names hints architecture used:

• pt_univenet - combination of Parallel Tacotron and pre-trained Univnet.