End-to-End Speech Recognition Models

This repository contains end-to-end automatic speech recognition models.This repository does not include training or audio or text preprocessing codes. If you want to see the code other than the model, please refer to here.
Many speech recognition open sources contain all the training-related code, making it hard to see only the model structure. So I have created a repository for only the models I've implemented and make them public.
I will continue to add to this the speech recognition models that I implement.

Implementation List

• Deep Speech 2
  Dario Amodei et al. Deep Speech2: End-to-End Speech Recognition in English and Mandarin
  SeanNaren. deepspeech.pytorch

• Listen, Attend and Spell (modified version)
  Wiliam Chan et al. Listen, Attend and Spell
  Takaaki Hori et al. Advances in Joint CTC-Attention based E2E ASR with a Deep CNN Encoder and RNN-LM
  IBM. Pytorch-seq2seq
  clovaai. ClovaCall

• Speech Transformer
  Ashish Vaswani et al. Attention Is All You Need
  Yuanyuan Zhao et al. The SpeechTransformer for Large-scale Mandarin Chinese Speech Recognition
  kaituoxu. Speech-Transformer

• Jasper
  Jason Li et al, Jasper: An End-to-End Convolutional Neural Acoustic Model
  NVIDIA. DeepLearningExample

• Voice Activity Detection (1 dimensional Resnet Model)
  filippogiruzzi. voice_activity_detection

Troubleshoots and Contributing

If you have any questions, bug reports, and feature requests, please open an issue on Github.

I appreciate any kind of feedback or contribution. Feel free to proceed with small issues like bug fixes, documentation improvement. For major contributions and new features, please discuss with the collaborators in corresponding issues.

Code Style

I follow PEP-8 for code style. Especially the style of docstrings is important to generate documentation.

License

This project is licensed under the Apache-2.0 LICENSE - see the LICENSE.md file for details

Author

• Soohwan Kim @sooftware
• Contacts: kaki.brain@kakaobrain.com