Imagen de Portada

Whisper-MLA: Reducing GPU Memory Consumption of ASR Models based on MHA2MLA Conversion

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Sen, Wei, Jianguo, Lu, Wenhuan, Yue, Xianghu, Li, Wei, Li, Qiang, Zhao, Pengcheng, Cai, Ming, Si, Luo
Formato:	Preprint
Publicado:	2026
Materias:	Sound Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

HalluAudio: A Comprehensive Benchmark for Hallucination Detection in Large Audio-Language Models
por: Zhao, Feiyu, et al.
Publicado: (2026)

SQ-Whisper: Speaker-Querying based Whisper Model for Target-Speaker ASR
por: Guo, Pengcheng, et al.
Publicado: (2024)

Integrated Multi-Level Knowledge Distillation for Enhanced Speaker Verification
por: Yang, Wenhao, et al.
Publicado: (2024)

Channel Adaptation for Speaker Verification Using Optimal Transport with Pseudo Label
por: Yang, Wenhao, et al.
Publicado: (2024)

Robust Channel Learning for Large-Scale Radio Speaker Verification
por: Yang, Wenhao, et al.
Publicado: (2024)

Target Speaker ASR with Whisper
por: Polok, Alexander, et al.
Publicado: (2024)

Towards Rehearsal-Free Multilingual ASR: A LoRA-based Case Study on Whisper
por: Xu, Tianyi, et al.
Publicado: (2024)

Simul-Whisper: Attention-Guided Streaming Whisper with Truncation Detection
por: Wang, Haoyu, et al.
Publicado: (2024)

Whisper-SV: Adapting Whisper for Low-data-resource Speaker Verification
por: Zhang, Li, et al.
Publicado: (2024)

Extending Whisper with prompt tuning to target-speaker ASR
por: Ma, Hao, et al.
Publicado: (2023)

Speech-to-See: End-to-End Speech-Driven Open-Set Object Detection
por: Lu, Wenhuan, et al.
Publicado: (2025)

Technopolitics at MLA.
por: Kesti, Julie
Publicado: (1992)

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining
por: Zhang, Yifan, et al.
Publicado: (2026)

Hearing More with Less: Multi-Modal Retrieval-and-Selection Augmented Conversational LLM-Based ASR
por: Mu, Bingshen, et al.
Publicado: (2025)

X-EcoMLA: Upcycling Pre-Trained Attention into MLA for Efficient and Extreme KV Compression
por: Li, Guihong, et al.
Publicado: (2025)

New Energy for MLA.
por: Shafer, Rita
Publicado: (1987)

MLA in San Diego
por: Savage, Noel
Publicado: (1972)

On the Role of Encoder Depth: Pruning Whisper and LoRA Fine-Tuning in SLAM-ASR
por: Kolluri, Ganesh Pavan Kartikeya Bharadwaj, et al.
Publicado: (2026)

TyphoonMLA: A Mixed Naive-Absorb MLA Kernel For Shared Prefix
por: Yüzügüler, Ahmet Caner, et al.
Publicado: (2025)

Investigation of Whisper ASR Hallucinations Induced by Non-Speech Audio
por: Barański, Mateusz, et al.
Publicado: (2025)

BrainWhisperer: Leveraging Large-Scale ASR Models for Neural Speech Decoding
por: Boccato, Tommaso, et al.
Publicado: (2026)

Improving Whisper's Recognition Performance for Under-Represented Language Kazakh Leveraging Unpaired Speech and Text
por: Li, Jinpeng, et al.
Publicado: (2024)

Whisper in Medusa's Ear: Multi-head Efficient Decoding for Transformer-based ASR
por: Segal-Feldman, Yael, et al.
Publicado: (2024)

Listening for "You": Enhancing Speech Image Retrieval via Target Speaker Extraction
por: Yang, Wenhao, et al.
Publicado: (2025)

Neighborhood Attention Transformer with Progressive Channel Fusion for Speaker Verification
por: Li, Nian, et al.
Publicado: (2024)

Analytic Class Incremental Learning for Sound Source Localization with Privacy Protection
por: Qian, Xinyuan, et al.
Publicado: (2024)

FlashMLA-ETAP: Efficient Transpose Attention Pipeline for Accelerating MLA Inference on NVIDIA H20 GPUs
por: Dege, Pengcuo, et al.
Publicado: (2025)

Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whisper
por: Thorbecke, Iuliia, et al.
Publicado: (2024)

Quantizing Whisper-small: How design choices affect ASR performance
por: Söhler, Arthur, et al.
Publicado: (2025)

WhisperKit: On-device Real-time ASR with Billion-Scale Transformers
por: Orhon, Atila, et al.
Publicado: (2025)

When Denoising Hinders: Revisiting Zero-Shot ASR with SAM-Audio and Whisper
por: Islam, Akif, et al.
Publicado: (2026)

WhisperAlign: Word-Boundary-Aware ASR and WhisperX-Anchored Pyannote Diarization for Long-Form Bengali Speech
por: Chowdhury, Aurchi, et al.
Publicado: (2026)

Efficient Scaling for LLM-based ASR
por: Mu, Bingshen, et al.
Publicado: (2025)

Speaking Clearly: A Simplified Whisper-Based Codec for Low-Bitrate Speech Coding
por: Zhang, Xin, et al.
Publicado: (2025)

CoAVT: A Cognition-Inspired Unified Audio-Visual-Text Pre-Training Model for Multimodal Processing
por: Yue, Xianghu, et al.
Publicado: (2024)

A Comparative Study of LLM-based ASR and Whisper in Low Resource and Code Switching Scenario
por: Song, Zheshu, et al.
Publicado: (2024)

Index-ASR Technical Report
por: Song, Zheshu, et al.
Publicado: (2025)

WhispEar: A Bi-directional Framework for Scaling Whispered Speech Conversion via Pseudo-Parallel Whisper Generation
por: Fang, Zihao, et al.
Publicado: (2026)

Overcoming Data Scarcity in Multi-Dialectal Arabic ASR via Whisper Fine-Tuning
por: Özyilmaz, Ömer Tarik, et al.
Publicado: (2025)

Marco-ASR: A Principled and Metric-Driven Framework for Fine-Tuning Large-Scale ASR Models for Domain Adaptation
por: Ni, Xuanfan, et al.
Publicado: (2025)