Li-Wei Chen

txya900619's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

published a dataset 4 days ago

united-link/brecioso-eval-250822

Viewer • Updated 13 days ago • 8.65k • 8

published a model 4 days ago

united-link/brecioso-e-model-taigi-20250901

Automatic Speech Recognition • 2B • Updated 4 days ago • 10

updated a model 4 days ago

united-link/brecioso-e-model-taigi-20250901-ct2

Updated 4 days ago • 2

published a model 4 days ago

united-link/brecioso-e-model-taigi-20250901-ct2

Updated 4 days ago • 2

updated a model 4 days ago

united-link/brecioso-e-model-taigi-20250901

Automatic Speech Recognition • 2B • Updated 4 days ago • 10

updated a dataset 6 days ago

txya900619/name_synthesized

Viewer • Updated 6 days ago • 20.2k • 98

published a dataset 7 days ago

txya900619/name_synthesized

Viewer • Updated 6 days ago • 20.2k • 98

upvoted a paper 7 days ago

VibeVoice Technical Report

Paper • 2508.19205 • Published 9 days ago • 120

updated a dataset 13 days ago

united-link/brecioso-eval-250822

Viewer • Updated 13 days ago • 8.65k • 8

upvoted 3 papers 14 days ago

NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

Paper • 2508.14444 • Published 16 days ago • 35

Representing Speech Through Autoregressive Prediction of Cochlear Tokens

Paper • 2508.11598 • Published 20 days ago • 17

DINOv3

Paper • 2508.10104 • Published 22 days ago • 232

updated 4 Spaces 14 days ago

Running on Zero

Hakka F5 TTS Test

📈

Generate Taiwanese Hakka speech from text

Running

8

8

Taiwanese Hakka TTS

💻

Generate Taiwanese Hakka speech from text

Running on Zero

Formosan F5 TTS

🌖

Generate audio from text using reference audio

Running on Zero

2

2

Formosan ASR

📚

Transcribe audio to text with dialect support

updated 3 Spaces 17 days ago

Running on Zero

Formosan F5 TTS

🌖

Generate audio from text using reference audio

Running on Zero

Formosan F5 TTS

🌖

Generate audio from text using reference audio

Running on Zero

Formosan F5 TTS

🌖

Generate audio from text using reference audio