Language-Specialized MOPD for Multilingual LLM-Based ASR Language-Specialized Multi-Teacher On-Policy Distillation for Multilingual LLM-Based ASR Paper • 2608.03610 • Published 11 days ago
Language-Specialized Multi-Teacher On-Policy Distillation for Multilingual LLM-Based ASR Paper • 2608.03610 • Published 11 days ago
NIM4-ASR NIM4-ASR is our in-house ASR model, optimized for parameter efficiency, hallucination mitigation, customization, and real-time streaming inference. NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Paper • 2604.18105 • Published Apr 20 • 3
NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Paper • 2604.18105 • Published Apr 20 • 3
Rethinking Entropy Allocation in LLM-based ASR Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs Paper • 2604.08003 • Published Apr 9 • 1
Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs Paper • 2604.08003 • Published Apr 9 • 1
Language-Specialized MOPD for Multilingual LLM-Based ASR Language-Specialized Multi-Teacher On-Policy Distillation for Multilingual LLM-Based ASR Paper • 2608.03610 • Published 11 days ago
Language-Specialized Multi-Teacher On-Policy Distillation for Multilingual LLM-Based ASR Paper • 2608.03610 • Published 11 days ago
Rethinking Entropy Allocation in LLM-based ASR Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs Paper • 2604.08003 • Published Apr 9 • 1
Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs Paper • 2604.08003 • Published Apr 9 • 1
NIM4-ASR NIM4-ASR is our in-house ASR model, optimized for parameter efficiency, hallucination mitigation, customization, and real-time streaming inference. NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Paper • 2604.18105 • Published Apr 20 • 3
NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR Paper • 2604.18105 • Published Apr 20 • 3