# ESPnet-ONNX: Bridging a Gap Between Research and Production

arXiv: https://arxiv.org/abs/2209.09756 · HTML: https://mlsanity.com/paper/2209.09756/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2022.

## Built on by (most cited first, 1 of 1)

- [A Generalized Optimization Engine (GOE) for Edge AI Inference Acceleration](https://mlsanity.com/paper/2608.28652/) (2026)

## Abstract (arXiv)

In the field of deep learning, researchers often focus on inventing novel neural network models and improving benchmarks. In contrast, application developers are interested in making models suitable for actual products, which involves optimizing a model for faster inference and adapting a model to various platforms (e.g., C++ and Python). In this work, to fill the gap between the two, we establish an effective procedure for optimizing a PyTorch-based research-oriented model for deployment, taking ESPnet, a widely used toolkit for speech processing, as an instance. We introduce different techniques to ESPnet, including converting a model into an ONNX format, fusing nodes in a graph, and quantizing parameters, which lead to approximately 1.3-2× speedup in various tasks (i.e., ASR, TTS, speech translation, and spoken language understanding) while keeping its performance without any additional training. Our ESPnet-ONNX will be publicly available at https://github.com/espnet/espnetonnx