TTS 0.22.0

Deep learning for Text to Speech by Coqui.

12-30-2021 248 words 2 minutes 0 views

Contents

Deep learning for Text to Speech by Coqui.

Stars: 28681, Watchers: 28681, Forks: 3336, Open Issues: 71

The coqui-ai/TTS repo was created 3 years ago and the last code push was 17 minutes ago.
The project is extremely popular with a mindblowing 28681 github stars!

How to Install tts

You can install tts using pip

pip install tts

or add it to a project with poetry

poetry add tts

Package Details

Author: Eren Gölge
License: MPL-2.0
Homepage: https://github.com/coqui-ai/TTS
PyPi:: https://pypi.org/project/TTS/
Documentation:: https://github.com/coqui-ai/TTS/wiki
GitHub Repo:: https://github.com/coqui-ai/TTS

Classifiers

Multimedia
Multimedia/Sound/Audio
Multimedia/Sound/Audio/Speech
Scientific/Engineering/Artificial Intelligence
Software Development
Software Development/Libraries/Python Modules

No tts pypi packages just yet.

Errors

A list of common tts errors.

Code Examples

Here are some tts code examples and snippets.

GitHub Issues

The tts package has 71 open issues on GitHub

[Feature request] how to export any of these models to ONNX? and inference via tensorrt?
IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1)
[Bug] Formatter document looks strange.
[Feature request] Partnership with Jami
update import for load_config and load_tts_samples
[Feature request] Is there any chance for a stdout streaming option?
[Bug] Inconsistent items order
[Bug] Interrogative sentences do not sound like questions
[Question] Implement preprocessing on datasets?
feat(tokenizer): add digraph support for TTSTokenizer
Tokenizer API (Rebased)
Update models (Rebased)
[Bug] TTS.tts.configs.shared_configs.CharactersConfig does not allow lists
[Bug] Document proper handling of digraphs
Add argument to enable dp speaker conditioning in VITS