Puyuan Peng's picture

9 1

Puyuan Peng

pyp1

·

https://jasonppy.github.io/

AI & ML interests

Speech/Audio Generation, Speech Processing, Multimodal Learning

Recent Activity

authored a paper 11 days ago

ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models

updated a model about 2 months ago

pyp1/Encodec_VoiceStar

published a model about 2 months ago

pyp1/Encodec_VoiceStar

View all activity

Organizations

Papers 1

arxiv:2505.13444

spaces 1

VoiceCraft

models 9

pyp1/Encodec_VoiceStar

Updated Apr 8 • 1

pyp1/VoiceStar

Updated Apr 6 • 2

pyp1/VoiceCraft

Text-to-Speech • Updated Aug 21, 2024 • 23 • 212

pyp1/VoiceCraft_615M_8cb1024_se

Text-to-Speech • Updated Aug 21, 2024 • 2

pyp1/VoiceCraft_330M_TTSEnhanced

Text-to-Speech • Updated Apr 25, 2024 • 78 • 1

pyp1/VoiceCraft_830M_TTSEnhanced

Text-to-Speech • Updated Apr 21, 2024 • 840 • 8

pyp1/VoiceCraft_giga330M

Text-to-Speech • Updated Apr 16, 2024 • 126

pyp1/VoiceCraft_giga830M

Text-to-Speech • Updated Apr 16, 2024 • 164

pyp1/VoiceCraft_gigaHalfLibri330M_TTSEnhanced_max16s

Text-to-Speech • Updated Apr 16, 2024 • 9 • 1

datasets 1

pyp1/VoiceCraft_RealEdit

Viewer • Updated Mar 25, 2024 • 7.89M • 42 • 5