ESPnet-EZ: Python-only ESPnet for Easy Fine-tuning and Integration

TL;DR

ESPnet-EZ is a Python-only extension of ESPnet that simplifies fine-tuning and integrating speech models with popular frameworks, reducing development effort and dependencies.

Contribution

It introduces a Python-only, Bash-free interface for ESPnet, enabling easier and faster speech model development and integration.

Findings

Reduces code writing by 2.7x for fine-tuning

Decreases dependencies by 6.7x

Simplifies model development process

Abstract

We introduce ESPnet-EZ, an extension of the open-source speech processing toolkit ESPnet, aimed at quick and easy development of speech models. ESPnet-EZ focuses on two major aspects: (i) easy fine-tuning and inference of existing ESPnet models on various tasks and (ii) easy integration with popular deep neural network frameworks such as PyTorch-Lightning, Hugging Face transformers and datasets, and Lhotse. By replacing ESPnet design choices inherited from Kaldi with a Python-only, Bash-free interface, we dramatically reduce the effort required to build, debug, and use a new model. For example, to fine-tune a speech foundation model, ESPnet-EZ, compared to ESPnet, reduces the number of newly written code by 2.7x and the amount of dependent code by 6.7x while dramatically reducing the Bash script dependencies. The codebase of ESPnet-EZ is publicly available.