Pith. sign in

REVIEW 1 cited by

Scaling Laws for Acoustic Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2106.09488 v1 pith:VOFTGECP submitted 2021-06-11 eess.AS cs.CLcs.LGcs.SD

classification eess.AScs.CLcs.LGcs.SD
keywords modelsizelawsscalingtrainingmodelslossacoustic
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

There is a recent trend in machine learning to increase model quality by growing models to sizes previously thought to be unreasonable. Recent work has shown that autoregressive generative models with cross-entropy objective functions exhibit smooth power-law relationships, or scaling laws, that predict model quality from model size, training set size, and the available compute budget. These scaling laws allow one to choose nearly optimal hyper-parameters given constraints on available training data, model parameter count, or training computation budget. In this paper, we demonstrate that acoustic models trained with an auto-predictive coding loss behave as if they are subject to similar scaling laws. We extend previous work to jointly predict loss due to model size, to training set size, and to the inherent "irreducible loss" of the task. We find that the scaling laws accurately match model performance over two orders of magnitude in both model size and training set size, and make predictions about the limits of model performance.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Towards Robust Speech Recognition for Jamaican Patois Music Transcription

    eess.AS 2025-07 reject novelty 5.0 of 10

    Fine-tuning Whisper on 42 hours of Jamaican Patois music improves transcription error rates, and a fitted power law predicts error from model and data size.

Pith tools