PyPI page
Home page
Author:
Sidharth Rajaram
License:
MIT
Summary:
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models. Original authors: Yinghao Aaron Li, Cong Han, Vinay S. Raghavan, Gavin Mischler, Nima Mesgarani.
Latest version:
0.1.6
Required dependencies:
accelerate
|
cached-path
|
einops
|
einops-exts
|
filelock
|
gruut
|
gruut-ipa
|
gruut-lang-en
|
huggingface-hub
|
langchain
|
librosa
|
matplotlib
|
munch
|
networkx
|
nltk
|
pydub
|
pyyaml
|
scipy
|
soundfile
|
torch
|
torchaudio
|
tqdm
|
transformers
|
typing
|
typing-extensions
Downloads last day:
92
Downloads last week:
572
Downloads last month:
2,515