3 results found Sort:

yl4579
StyleTTS2 yl4579
427
5.1k
mit
76
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
gan tts wavlm pytorch deep-learning text-to-speech diffusion-models latent-diffusion speech-synthesis speaker-adaptation adversarial-training latent-diffusion-models
Created 2023-06-14
112 commits to main branch, last one 9 months ago
s3prl
s3prl s3prl
486
2.3k
apache-2.0
47
Self-Supervised Speech Pre-training and Representation Learning Toolkit
apc cpc pase tera wavlm decoar hubert vq-apc decoar2 wav2vec data2vec wav2vec2 mockingjay vq-wav2vec distilhubert unispeech-sat speech-pretraining speech-representation representation-learning self-supervised-learning
Created 2019-07-15
3,184 commits to main branch, last one about a month ago
wenet-e2e
wespeaker wenet-e2e
124
770
apache-2.0
16
Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit
asv ssl dino plda tdnn wavlm repvgg resnet cnceleb pytorch xvector campplus eres2net nist-sre voxceleb ecapa-tdnn production-ready speaker-diarization speaker-recognition speaker-verification
Created 2021-09-28
307 commits to master branch, last one 19 days ago