# Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling

arXiv: https://arxiv.org/abs/2311.00430 · HTML: https://mlsanity.com/paper/2311.00430/

## Key facts

- Cited by 90 papers in the map (data through 14 Oct 2026).
- Placed in Speech and audio distillation, one of 12 directions in Knowledge distillation.
- Builds on 46 of its 73 references that are in the map.
- First posted on arXiv 1 Nov 2023.

## Placed in

- Knowledge distillation / [Speech and audio distillation](https://mlsanity.com/distill/speech-and-audio-distillation/)

## Builds on (most cited first, 30 of 46)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [Sequence-Level Knowledge Distillation](https://mlsanity.com/paper/1606.07947/) (2016)
- [The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation](https://mlsanity.com/paper/2106.03193/) (2021)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [Datasets: A Community Library for Natural Language Processing](https://mlsanity.com/paper/2109.02846/) (2021)
- [MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices](https://mlsanity.com/paper/2004.02984/) (2020)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation](https://mlsanity.com/paper/2101.00390/) (2021)
- [Measuring Robustness to Natural Distribution Shifts in Image Classification](https://mlsanity.com/paper/2007.00644/) (2020)
- [GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio](https://mlsanity.com/paper/2106.06909/) (2021)
- [WhisperX: Time-Accurate Speech Transcription of Long-Form Audio](https://mlsanity.com/paper/2303.00747/) (2023)
- [Confident Adaptive Language Modeling](https://mlsanity.com/paper/2207.07061/) (2022)
- [Streaming End-to-end Speech Recognition For Mobile Devices](https://mlsanity.com/paper/1811.06621/) (2018)

## Built on by (most cited first, 30 of 90)

- [VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos](https://mlsanity.com/paper/2502.01549/) (2025)
- [OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer](https://mlsanity.com/paper/2401.16658/) (2024)
- [WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning](https://mlsanity.com/paper/2512.02425/) (2025)
- [OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification](https://mlsanity.com/paper/2402.12654/) (2024)
- [Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling](https://mlsanity.com/paper/2509.08753/) (2025)
- [Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation](https://mlsanity.com/paper/2510.06961/) (2025)
- [Scaling Rich Style-Prompted Text-to-Speech Datasets](https://mlsanity.com/paper/2503.04713/) (2025)
- [Lost in Transcription, Found in Distribution Shift: Demystifying Hallucination in Speech Foundation Models](https://mlsanity.com/paper/2502.12414/) (2025)
- [The BabyView dataset: High-resolution egocentric videos of infants' and young children's everyday experiences](https://mlsanity.com/paper/2406.10447/) (2024)
- [Distillation of Diffusion Features for Semantic Correspondence](https://mlsanity.com/paper/2412.03512/) (2024)
- [TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling](https://mlsanity.com/paper/2504.07053/) (2025)
- [Calm-Whisper: Reduce Whisper Hallucination On Non-Speech By Calming Crazy Heads Down](https://mlsanity.com/paper/2505.12969/) (2025)
- [Afrispeech-Dialog: A Benchmark Dataset for Spontaneous English Conversations in Healthcare and Beyond](https://mlsanity.com/paper/2502.03945/) (2025)
- [Training and Inference Efficiency of Encoder-Decoder Speech Models](https://mlsanity.com/paper/2503.05931/) (2025)
- [NeKo: Cross-Modality Post-Recognition Error Correction with Tasks-Guided Mixture-of-Experts Language Model](https://mlsanity.com/paper/2411.05945/) (2024)
- [LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation](https://mlsanity.com/paper/2502.20583/) (2025)
- [SceneRAG: Scene-level Retrieval-Augmented Generation for Video Understanding](https://mlsanity.com/paper/2506.07600/) (2025)
- [Efficient and Robust Speaker Diarization via Structured Pruning of Self-Supervised Models](https://mlsanity.com/paper/2506.18623/) (2025)
- [MPC-Minimized Secure LLM Inference](https://mlsanity.com/paper/2408.03561/) (2024)
- [Whisper in Medusa's Ear: Multi-head Efficient Decoding for Transformer-based ASR](https://mlsanity.com/paper/2409.15869/) (2024)
- [Leave No Knowledge Behind During Knowledge Distillation: Towards Practical and Effective Knowledge Distillation for Code-Switching ASR Using Realistic Data](https://mlsanity.com/paper/2407.10603/) (2024)
- [Whisper-LM: Improving ASR Models with Language Models for Low-Resource Languages](https://mlsanity.com/paper/2503.23542/) (2025)
- [Efficient Speech Translation through Model Compression and Knowledge Distillation](https://mlsanity.com/paper/2505.20237/) (2025)
- [Whispering in Norwegian: Navigating Orthographic and Dialectic Challenges](https://mlsanity.com/paper/2402.01917/) (2024)
- [To Distill or Not to Distill? On the Robustness of Robust Knowledge Distillation](https://mlsanity.com/paper/2406.04512/) (2024)
- [The Greek podcast corpus: Competitive speech models for low-resourced languages with weakly supervised data](https://mlsanity.com/paper/2406.15284/) (2024)
- [uDistil-Whisper: Label-Free Data Filtering for Knowledge Distillation in Low-Data Regimes](https://mlsanity.com/paper/2407.01257/) (2024)
- [BaldWhisper: Faster Whisper with Head Shearing and Layer Merging](https://mlsanity.com/paper/2510.08599/) (2025)
- [Iterative Layer Pruning for Efficient Translation Inference](https://mlsanity.com/paper/2510.22763/) (2025)
- [Outlier Reduction with Gated Attention for Improved Post-training Quantization in Large Sequence-to-sequence Speech Foundation Models](https://mlsanity.com/paper/2406.11022/) (2024)

## Abstract (arXiv)

As the size of pre-trained speech recognition models increases, running these large models in low-latency or resource-constrained environments becomes challenging. In this work, we leverage pseudo-labelling to assemble a large-scale open-source dataset which we use to distill the Whisper model into a smaller variant, called Distil-Whisper. Using a simple word error rate (WER) heuristic, we select only the highest quality pseudo-labels for training. The distilled model is 5.8 times faster with 51% fewer parameters, while performing to within 1% WER on out-of-distribution test data in a zero-shot transfer setting. Distil-Whisper maintains the robustness of the Whisper model to difficult acoustic conditions, while being less prone to hallucination errors on long-form audio. Distil-Whisper is designed to be paired with Whisper for speculative decoding, yielding a 2 times speed-up while mathematically ensuring the same outputs as the original model. To facilitate further research in this domain, we make our training code, inference code and models publicly accessible.