ESPnet-EZ: Python-only ESPnet for Easy Fine-tuning and Integration
This work addresses the problem of high development effort for speech model researchers and practitioners by providing an incremental improvement to an existing toolkit.
The paper tackles the complexity of using the ESPnet speech processing toolkit by introducing ESPnet-EZ, a Python-only extension that simplifies fine-tuning and integration with popular frameworks, reducing newly written code by 2.7x and dependent code by 6.7x.
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.