14 162 18

Li-Wei Chen

txya900619

AI & ML interests

None yet

Recent Activity

upvoted a paper about 22 hours ago

SageAttention2++: A More Efficient Implementation of SageAttention2

updated a Space 1 day ago

united-link/formosan-f5-tts

updated a model 1 day ago

ithuan/f5-tts-formosan-all-finetune

View all activity

Organizations

txya900619's activity

upvoted a paper about 22 hours ago

SageAttention2++: A More Efficient Implementation of SageAttention2

Paper • 2505.21136 • Published 3 days ago • 35

updated a Space 1 day ago

Formosan F5 TTS

🌖

Generate audio from text using reference audio

updated a model 1 day ago

ithuan/f5-tts-formosan-all-finetune

Text-to-Speech • Updated 1 day ago

liked a model 2 days ago

stabilityai/stable-audio-open-small

Text-to-Audio • Updated 3 days ago • 4.48k • 188

upvoted a paper 3 days ago

Shifting AI Efficiency From Model-Centric to Data-Centric Compression

Paper • 2505.19147 • Published 5 days ago • 136

upvoted a paper 5 days ago

MMaDA: Multimodal Large Diffusion Language Models

Paper • 2505.15809 • Published 9 days ago • 83

updated a model 7 days ago

ithuan/f5-tts-formosan-all-finetune-with-word

Text-to-Speech • Updated 7 days ago

published a model 7 days ago

ithuan/f5-tts-formosan-all-finetune

Text-to-Speech • Updated 1 day ago

upvoted a paper 8 days ago

Chain-of-Model Learning for Language Model

Paper • 2505.11820 • Published 14 days ago • 109

liked a model 8 days ago

google/gemma-3n-E4B-it-litert-preview

Image-Text-to-Text • Updated 4 days ago • 669

upvoted 2 papers 10 days ago

Parallel Scaling Law for Language Models

Paper • 2505.10475 • Published 15 days ago • 75

DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception

Paper • 2505.04410 • Published 23 days ago • 43

published a model 12 days ago

ithuan/f5-tts-formosan-all-finetune-with-word

Text-to-Speech • Updated 7 days ago

upvoted 2 papers 12 days ago

Fast Text-to-Audio Generation with Adversarial Post-Training

Paper • 2505.08175 • Published 18 days ago • 22

MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder

Paper • 2505.07916 • Published 18 days ago • 119

updated a model 14 days ago

formospeech/whisper-large-v2-formosan-all

Automatic Speech Recognition • Updated 14 days ago • 77

New activity in formospeech/yourtts-htia-240704 14 days ago

How to train other hakka ?

#1 opened 15 days ago by

lukeewin

updated a dataset 18 days ago

txya900619/wavcaps-10s-16k

Viewer • Updated 18 days ago • 187k • 702 • 1

upvoted 2 papers 19 days ago

Flow-GRPO: Training Flow Matching Models via Online RL

Paper • 2505.05470 • Published 22 days ago • 76

VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model

Paper • 2505.03739 • Published 24 days ago • 8