Hung-yi Lee

hungyilee's activity

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

liked a dataset 4 months ago

wizzzzzzzzz/TTS_audio

Viewer • Updated May 22, 2025 • 8.2k • 15 • 2

updated a Space 8 months ago

Configuration error

SpeechLLM Leaderboard

🚀

published a Space 8 months ago

Configuration error

SpeechLLM Leaderboard

🚀

updated a Space 8 months ago

Configuration error

Spoken Llm Leaderboard

🚀

published a Space 8 months ago

Configuration error

Spoken Llm Leaderboard

🚀

liked a Space 9 months ago

Running

5

Leaderboard

📈

5

Display and filter leaderboard data

liked a model 9 months ago

DeSTA-ntu/DeSTA2.5-Audio-Llama-3.1-8B

Audio-Text-to-Text • 0.1B • Updated Oct 15, 2025 • 495 • 6

authored a paper 10 months ago

A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data

Paper • 2506.11130 • Published Jun 10, 2025 • 5

authored a paper 11 months ago

Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey

Paper • 2505.15957 • Published May 21, 2025 • 3

liked 2 datasets about 1 year ago

voidful/tw_exam_hard

Viewer • Updated Jun 30, 2025 • 1.53k • 3 • 2

HKUSTAudio/Audio-FLAN-Dataset

Preview • Updated Oct 6, 2025 • 123k • 42

liked a model about 1 year ago

voidful/Llama-Typhoon-8B-R1

Feature Extraction • 9B • Updated Feb 26, 2025 • 5 • 9

liked 2 Spaces about 1 year ago

Build error

Agents

11

BreezyVoice

🎛

11

Generate audio from text using a prompt sample

Running

Agents

30

BreezyVoice

🎛

30

Generate realistic voice from text and audio sample

upvoted a paper about 1 year ago

BreezyVoice: Adapting TTS for Taiwanese Mandarin with Enhanced Polyphone Disambiguation -- Challenges and Insights

Paper • 2501.17790 • Published Jan 29, 2025 • 3

authored a paper over 1 year ago

Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging

Paper • 2412.19512 • Published Dec 27, 2024 • 9

liked a dataset over 1 year ago

voidful/gen_ai_2024

Viewer • Updated Aug 22, 2024 • 14.9k • 18 • 2

liked a model almost 2 years ago

andybi7676/cool-whisper

Updated Jul 18, 2024 • 50

authored a paper almost 2 years ago

DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging

Paper • 2407.01470 • Published Jul 1, 2024 • 7