https://github.com/yqzhishen/onnxcrepe

ONNX deployment of the CREPE pitch tracker
https://github.com/yqzhishen/onnxcrepe

crepe music-information-retrieval onnx onnxruntime pitch-estimation pitch-tracking

Last synced: 21 days ago
JSON representation

ONNX deployment of the CREPE pitch tracker

• Host: GitHub
• URL: https://github.com/yqzhishen/onnxcrepe
• Owner: yqzhishen
• License: mit
• Created: 2022-10-18T11:56:15.000Z (about 3 years ago)
• Default Branch: main
• Last Pushed: 2022-10-27T18:04:36.000Z (about 3 years ago)
• Last Synced: 2025-04-23T16:22:38.364Z (7 months ago)
• Topics: crepe, music-information-retrieval, onnx, onnxruntime, pitch-estimation, pitch-tracking
• Language: Python
• Homepage:
• Size: 6.16 MB
• Stars: 21
• Watchers: 3
• Forks: 2
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# onnxcrepe

[![License](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)

ONNX deployment of the CREPE [1] pitch tracker. The provided model weights and most of the codes in this repository were converted and migrated from the original TensorFlow implementation [here](https://github.com/marl/crepe/) and Max Morrison's [torchcrepe](https://github.com/maxrmorrison/torchcrepe), a PyTorch implementation of CREPE.

## Usage

Download model weights from [releases](https://github.com/yqzhishen/onnxcrepe/releases) and put them into the `onnxcrepe/assets/` directory. See demo [here](samples/demo.py).

Documentation of this repository is still a work in progress and is comming soon.

## Acknowledgements

Codes and model weights in this repository are based on the following repos:

- [torchcrepe](https://github.com/maxrmorrison/torchcrepe) for 'full' and 'tiny' model weights and most of the code implementation

- [Weights_Keras_2_Pytorch](https://github.com/AgCl-LHY/Weights_Keras_2_Pytorch) for converting 'large', 'medium' and 'small' model weights from the original implementation

- [PyTorch](https://github.com/pytorch/pytorch) for exporting onnx models

- [onnx-optimizer](https://github.com/onnx/optimizer) and [onnx-simplifier](https://github.com/daquexian/onnx-simplifier) for optimizing performance

- [onnxruntime](https://github.com/microsoft/onnxruntime) for execution and configurations

## References

[1] J. W. Kim, J. Salamon, P. Li, and J. P. Bello, “[Crepe: A Convolutional Representation for Pitch Estimation](https://arxiv.org/abs/1802.06182),” in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).