# Big model only for hard audios: Sample dependent Whisper model selection for efficient inferences

arXiv: https://arxiv.org/abs/2309.12712 · HTML: https://mlsanity.com/paper/2309.12712/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 30 references that are in the map.
- First posted on arXiv 22 Sep 2023.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages](https://mlsanity.com/paper/2303.01037/) (2023)
- [Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition](https://mlsanity.com/paper/2305.05084/) (2023)
- [Unsupervised pretraining transfers well across languages](https://mlsanity.com/paper/2002.02848/) (2020)
- [Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers](https://mlsanity.com/paper/2307.03183/) (2023)
- [Probing phoneme, language and speaker information in unsupervised speech representations](https://mlsanity.com/paper/2203.16193/) (2022)
- [MoLE : Mixture of Language Experts for Multi-Lingual Automatic Speech Recognition](https://mlsanity.com/paper/2302.13750/) (2023)
- [Speech Self-Supervised Representation Benchmarking: Are We Doing it Right?](https://mlsanity.com/paper/2306.00452/) (2023)
- [Brouhaha: multi-task training for voice activity detection, speech-to-noise ratio, and C50 room acoustics estimation](https://mlsanity.com/paper/2210.13248/) (2022)
- [CommonAccent: Exploring Large Acoustic Pretrained Models for Accent Classification Based on Common Voice](https://mlsanity.com/paper/2305.18283/) (2023)
- [Hey ASR System! Why Aren't You More Inclusive? Automatic Speech Recognition Systems' Bias and Proposed Bias Mitigation Techniques. A Literature Review](https://mlsanity.com/paper/2211.09511/) (2022)
- [Mixture-of-Expert Conformer for Streaming Multilingual ASR](https://mlsanity.com/paper/2305.15663/) (2023)
- [Speech Self-Supervised Representations Benchmarking: a Case for Larger Probing Heads](https://mlsanity.com/paper/2308.14456/) (2023)
- [Fine-tuning Strategies for Faster Inference using Speech Self-Supervised Models: A Comparative Study](https://mlsanity.com/paper/2303.06740/) (2023)
- [HuBERT-EE: Early Exiting HuBERT for Efficient Speech Recognition](https://mlsanity.com/paper/2204.06328/) (2022)
- [Word Error Rate Estimation Without ASR Output: e-WER2](https://mlsanity.com/paper/2008.03403/) (2020)
- [WER-BERT: Automatic WER Estimation with BERT in a Balanced Ordinal Classification Paradigm](https://mlsanity.com/paper/2101.05478/) (2021)
- [Multilingual Word Error Rate Estimation: e-WER3](https://mlsanity.com/paper/2304.00649/) (2023)
- [Surprisal-Triggered Conditional Computation with Neural Networks](https://mlsanity.com/paper/2006.01659/) (2020)

## Built on by (most cited first, 2 of 2)

- [Looking Beyond The Top-1: Transformers Determine Top Tokens In Order](https://mlsanity.com/paper/2410.20210/) (2024)
- [uDistil-Whisper: Label-Free Data Filtering for Knowledge Distillation in Low-Data Regimes](https://mlsanity.com/paper/2407.01257/) (2024)

## Abstract (arXiv)

Recent progress in Automatic Speech Recognition (ASR) has been coupled with a substantial increase in the model sizes, which may now contain billions of parameters, leading to slow inferences even with adapted hardware. In this context, several ASR models exist in various sizes, with different inference costs leading to different performance levels. Based on the observation that smaller models perform optimally on large parts of testing corpora, we propose to train a decision module, that would allow, given an audio sample, to use the smallest sufficient model leading to a good transcription. We apply our approach to two Whisper models with different sizes. By keeping the decision process computationally efficient, we build a decision module that allows substantial computational savings with reduced performance drops.