coqui-ai/TTS: v0.6.0
Creators
- Eren Gölge1
- Edresson Casanova2
- WeberJulian
- Alexander Korolev
- Thomas Werkmeister
- Reuben Morais
- Thorsten Müller
- Kirian Guiller
- Branislav Gerazov3
- Thorben Hellweg4
- Jörg Thalheim5
- Ayush Chaurasia
- Katsuya Iida
- Neil Stoker
- Rishikesh (ऋषिकेश)6
- Michael Hansen
- Adonis Pujols
- bgerazov
- mittimithai
- Agrin Hilmkil7
- Markus Toman
- geneing
- Guy Elsmore-Paddock8
- Martin Weinelt
- QP Hou
- jyegerlehner
- a-froghyar
- Anand...
- Bajibabu Bollepalli9
- 1. Coqui.ai
- 2. University of São Paulo (USP)
- 3. Faculty of Electrical Engineering and Information Technologies
- 4. University of Münster (WWU)
- 5. no
- 6. Open Source
- 7. @Storytel
- 8. Inveniem
- 9. Aalto University
Description
What's Changed Tokenizer API
Tokenizer API is defined by the TTSTokenizer class. It is intended to provide all the text processing functionalities to a tts model. New tokenizers can also be added by subclassing the TTSTokenizer class.
Phonemizer APIPhonemizer API is defined by the BasePhonemizer class and implemented by the ESpeak and Gruut wrappers, ZH_CH, JP_JA phonemizers. New phonemizers can be added by implementing the BasePhonemizer class.
BaseCharactersBaseCharacters class provides an API to define the model vocabulary and provide the dictionary to map characters to token IDs and back. There are two pre-defined classes inheriting from BaseCharacters. IPAPhonemes and Graphemes that respectively define the IPA phoneme character set for models using phonemes and grapheme set for models using raw characters.
Punctuations classPunctuations class to strip out punctuations and restore them when needed.
Language specific text normalization routines underTTS.tts.utils.text
Under TTS.tts.utils.text
there are folders for each language to accommodate the text normalization routines that
are designed for the language.
We separate the trainer as a new repo 👟Trainer. It is a general-purpose model trainer for Pytorch with certain design choices in mind.
- Support for different experiment tracking dashboards like ClearML, Tensorboard, MLFlow, and W&Bs.
- Flexible to train any kind of DL model.
- Simple code base and easily expandable.
- Easy to debug.
It is a very early-stage and monolithic library currently. Feel free to share your ✨feedback✨ and ✨contribute✨.
VITS implementation updateWith this version of VITS model, we get rid of some of the issues that affect the model performance. It also illustrates well how you could adapt any open-source model implementation to 🐸TTS and 👟Trainer without even knowing the rest for 🐸TTS library.
Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.5.0...v0.6.0
Files
coqui-ai/TTS-v0.6.0.zip
Files
(13.6 MB)
Name | Size | Download all |
---|---|---|
md5:301d9f932b6942632c610d59fde50fb7
|
13.6 MB | Preview Download |
Additional details
Related works
- Is supplement to
- https://github.com/coqui-ai/TTS/tree/v0.6.0 (URL)