Wenxi Chen

worstchan

·

https://cwx-worst-one.github.io/

cwx-worst-one

AI & ML interests

understanding & generation in speech and audio

Recent Activity

updated a model 29 days ago

worstchan/WavTTS

new activity about 1 month ago

worstchan/WavTTS:FP8 Quantization?

authored a paper about 1 month ago

WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling

View all activity

Organizations

upvoted a collection 4 months ago

SoulX-Duplug

3 items • Updated Mar 17 • 5

upvoted a paper 8 months ago

SoulX-Podcast: Towards Realistic Long-form Podcasts with Dialectal and Paralinguistic Diversity

Paper • 2510.23541 • Published Oct 27, 2025 • 17

upvoted a collection 8 months ago

SoulX-Podcast

Models of SoulX-Podcast • 3 items • Updated Mar 2 • 47

upvoted a collection 9 months ago

SAC

Models of the SAC speech codec • 3 items • Updated Dec 2, 2025 • 3

upvoted an article 9 months ago

Article

Efficient LLM Pretraining: Packed Sequences and Masked Attention

sirluk

•

Oct 7, 2024

• 71