Image de couverture de livre

On the Role of Encoder Depth: Pruning Whisper and LoRA Fine-Tuning in SLAM-ASR

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kolluri, Ganesh Pavan Kartikeya Bharadwaj, Kampouridis, Michael, Shekhar, Ravi
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Sound
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Towards Rehearsal-Free Multilingual ASR: A LoRA-based Case Study on Whisper
par: Xu, Tianyi, et autres
Publié: (2024)

Efficient Multilingual ASR Finetuning via LoRA Language Experts
par: Li, Jiahong, et autres
Publié: (2025)

Overcoming Data Scarcity in Multi-Dialectal Arabic ASR via Whisper Fine-Tuning
par: Özyilmaz, Ömer Tarik, et autres
Publié: (2025)

A Language-Agnostic Hierarchical LoRA-MoE Architecture for CTC-based Multilingual ASR
par: Zheng, Yuang, et autres
Publié: (2026)

Language Family Matters: Evaluating LLM-Based ASR Across Linguistic Boundaries
par: Zhang, Yuchen, et autres
Publié: (2026)

Zipper-LoRA: Dynamic Parameter Decoupling for Speech-LLM based Multilingual Speech Recognition
par: Mei, Yuxiang, et autres
Publié: (2026)

UtterTune: LoRA-Based Target-Language Pronunciation Edit and Control in Multilingual Text-to-Speech
par: Kato, Shuhei
Publié: (2025)

LoRA-Whisper: Parameter-Efficient and Extensible Multilingual ASR
par: Song, Zheshu, et autres
Publié: (2024)

Noise-Robust AV-ASR Using Visual Features Both in the Whisper Encoder and Decoder
par: Li, Zhengyang, et autres
Publié: (2026)

Extending Whisper with prompt tuning to target-speaker ASR
par: Ma, Hao, et autres
Publié: (2023)

Sparsely Shared LoRA on Whisper for Child Speech Recognition
par: Liu, Wei, et autres
Publié: (2023)

Enhancing Aviation Communication Transcription: Fine-Tuning Distil-Whisper with LoRA
par: Mirzaei, Shokoufeh, et autres
Publié: (2025)

Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whisper
par: Thorbecke, Iuliia, et autres
Publié: (2024)

Quantizing Whisper-small: How design choices affect ASR performance
par: Söhler, Arthur, et autres
Publié: (2025)

WhisperKit: On-device Real-time ASR with Billion-Scale Transformers
par: Orhon, Atila, et autres
Publié: (2025)

CLiFT-ASR: A Cross-Lingual Fine-Tuning Framework for Low-Resource Taiwanese Hokkien Speech Recognition
par: Sung, Hung-Yang, et autres
Publié: (2025)

Pruning as Regularization: Sensitivity-Aware One-Shot Pruning in ASR
par: Irigoyen, Julian, et autres
Publié: (2025)

HDMoLE: Mixture of LoRA Experts with Hierarchical Routing and Dynamic Thresholds for Fine-Tuning LLM-based ASR Models
par: Mu, Bingshen, et autres
Publié: (2024)

ID-LoRA: Identity-Driven Audio-Video Personalization with In-Context LoRA
par: Dahan, Aviad, et autres
Publié: (2026)

Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder
par: Shakeel, Muhammad, et autres
Publié: (2025)

Effective Text Adaptation for LLM-based ASR through Soft Prompt Fine-Tuning
par: Ma, Yingyi, et autres
Publié: (2024)

DR-LoRA: Dynamic Rank LoRA for Fine-Tuning Mixture-of-Experts Models
par: Deng, Guanzhi, et autres
Publié: (2026)

HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning
par: Tian, Chunlin, et autres
Publié: (2024)

SloPal: A 60-Million-Word Slovak Parliamentary Corpus with Aligned Speech and Fine-Tuned ASR Models
par: Božík, Erik, et autres
Publié: (2025)

Moonshine v2: Ergodic Streaming Encoder ASR for Latency-Critical Speech Applications
par: Kudlur, Manjunath, et autres
Publié: (2026)

SAML: Speaker Adaptive Mixture of LoRA Experts for End-to-End ASR
par: Zhao, Qiuming, et autres
Publié: (2024)

Whisper Turns Stronger: Augmenting Wav2Vec 2.0 for Superior ASR in Low-Resource Languages
par: Anidjar, Or Haim, et autres
Publié: (2024)

LoRA-drop: Efficient LoRA Parameter Pruning based on Output Evaluation
par: Zhou, Hongyun, et autres
Publié: (2024)

Are Transformers in Pre-trained LM A Good ASR Encoder? An Empirical Study
par: An, Keyu, et autres
Publié: (2024)

Performance Analysis of Speech Encoders for Low-Resource SLU and ASR in Tunisian Dialect
par: Mdhaffar, Salima, et autres
Publié: (2024)

CantoASR: Prosody-Aware ASR-LALM Collaboration for Low-Resource Cantonese
par: Chen, Dazhong, et autres
Publié: (2025)

KD-LoRA: A Hybrid Approach to Efficient Fine-Tuning with LoRA and Knowledge Distillation
par: Azimi, Rambod, et autres
Publié: (2024)

Behind the Scenes: Mechanistic Interpretability of LoRA-adapted Whisper for Speech Emotion Recognition
par: Ma, Yujian, et autres
Publié: (2025)

UniEnc-CASSNAT: An Encoder-only Non-autoregressive ASR for Speech SSL Models
par: Fan, Ruchao, et autres
Publié: (2024)

Performance evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forward
par: Kumar, Shashi, et autres
Publié: (2024)

Revealing the Role of Audio Channels in ASR Performance Degradation
par: Huang, Kuan-Tang, et autres
Publié: (2025)

L1RA: Dynamic Rank Assignment in LoRA Fine-Tuning
par: Singh, Raul, et autres
Publié: (2025)

A Comparative Study of LLM-based ASR and Whisper in Low Resource and Code Switching Scenario
par: Song, Zheshu, et autres
Publié: (2024)

LoRA-Squeeze: Simple and Effective Post-Tuning and In-Tuning Compression of LoRA Modules
par: Vulić, Ivan, et autres
Publié: (2026)

Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs
par: Xie, Yuan, et autres
Publié: (2026)