https://github.com/mddct/jax-rnnt-loss
https://github.com/mddct/jax-rnnt-loss
Last synced: 3 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/mddct/jax-rnnt-loss
- Owner: Mddct
- Created: 2024-10-16T10:03:56.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-10-16T13:56:48.000Z (over 1 year ago)
- Last Synced: 2025-04-30T06:09:58.765Z (about 1 year ago)
- Language: Python
- Size: 9.77 KB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## Thanks to [JAX](https://github.com/google/jax) and Apple's project [axlearn](https://github.com/apple/axlearn), we can now compute RNNT loss in pure JAX—so efficient
## Citation
```
@misc{graves2012sequencetransductionrecurrentneural,
title={Sequence Transduction with Recurrent Neural Networks},
author={Alex Graves},
year={2012},
eprint={1211.3711},
archivePrefix={arXiv},
primaryClass={cs.NE},
url={https://arxiv.org/abs/1211.3711},
}
@INPROCEEDINGS{8639690,
author={Bagby, Tom and Rao, Kanishka and Sim, Khe Chai},
booktitle={2018 IEEE Spoken Language Technology Workshop (SLT)},
title={Efficient Implementation of Recurrent Neural Network Transducer in Tensorflow},
year={2018},
volume={},
number={},
pages={506-512},
keywords={Computational modeling;Graphics processing units;Transducers;Acoustics;Recurrent neural networks;Hidden Markov models;Benchmark testing;recurrent neural network transducer;forward-backward algorithm;TensorFlow;GPU;TPU},
doi={10.1109/SLT.2018.8639690}}
@misc{variani2020hybridautoregressivetransducerhat,
title={Hybrid Autoregressive Transducer (hat)},
author={Ehsan Variani and David Rybach and Cyril Allauzen and Michael Riley},
year={2020},
eprint={2003.07705},
archivePrefix={arXiv},
primaryClass={eess.AS},
url={https://arxiv.org/abs/2003.07705},
}
```