You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
Daniel Muckerman e5ec86c9fd Fix model names 4 years ago
fastspeech_squeezewave@839ea13617 Initial commit 4 years ago
tacotron2@185cd24e04 Initial commit 4 years ago
.gitignore Initial commit 4 years ago
.gitmodules Initial commit 4 years ago
Dockerfile Update dockerfile 4 years ago
README.md Initial commit 4 years ago
merged.dict_1.1.txt Initial commit 4 years ago
requirements.txt Initial commit 4 years ago
synthesize.py Fix model names 4 years ago

README.md

Tia TTS

Experimental TTS for CPU inference using Tacotron2 and Squeezewave.

Install

Initialize the submodules: git submodule update --init --recursive

Install the python dependencies: pip install -r requirements.txt

Copy your models into the directory. This was trained on 22khz tacotron2 and squeezewave models. Squeezewave is loaded using a state_dict so we can take advantage of the existing pretrained models provided by the paper's author while maintaining compatibility with the tweaked architecture to enable denoising without necessitating retraining the vocoder.

Run the project: python synthesize.py