Recent Developments on ESPnet Toolkit Boosted by Conformer
This work reduces the burden of preparing high-resource research environments for the speech processing community by providing open-source recipes and pre-trained models.
The study presents recent developments in the ESPnet toolkit by integrating the Conformer architecture, showing competitive or superior performance compared to current state-of-the-art Transformer models across tasks like ASR, ST, SS, and TTS.
In this study, we present recent developments on ESPnet: End-to-End Speech Processing toolkit, which mainly involves a recently proposed architecture called Conformer, Convolution-augmented Transformer. This paper shows the results for a wide range of end-to-end speech processing applications, such as automatic speech recognition (ASR), speech translations (ST), speech separation (SS) and text-to-speech (TTS). Our experiments reveal various training tips and significant performance benefits obtained with the Conformer on different tasks. These results are competitive or even outperform the current state-of-art Transformer models. We are preparing to release all-in-one recipes using open source and publicly available corpora for all the above tasks with pre-trained models. Our aim for this work is to contribute to our research community by reducing the burden of preparing state-of-the-art research environments usually requiring high resources.