Jiaqi Song

Jiaqi1Song

5 2

·

AI & ML interests

Large Audio Language Model, Omni Model, NLP, World Model

Recent Activity

liked a dataset about 1 month ago

upvoted a collection 2 months ago

upvoted a paper 2 months ago

Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation

View all activity

Organizations

None yet

upvoted a collection 2 months ago

NIM4-ASR

NIM4-ASR is our in-house ASR model, optimized for parameter efficiency, hallucination mitigation, customization, and real-time streaming inference. • 1 item • Updated Jun 18 • 3

upvoted a paper 2 months ago

Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation

Paper • 2605.19833 • Published May 19 • 137

upvoted 2 collections 2 months ago

WenetSpeech-Wu

4 items • Updated Jan 31 • 6

Rethinking Entropy Allocation in LLM-based ASR

1 item • Updated Jun 11 • 2

upvoted a paper 2 months ago

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR

Paper • 2604.18105 • Published Apr 20 • 3