# Speech Recognition

## Links

{% embed url="<https://matthewkaras.medium.com/25-years-in-speech-technology-d5f9dfd98429>" %}

* ​[HN: Facebook open-sources a speech-recognition system and a machine learning library (2018)](https://news.ycombinator.com/item?id=18736116)​
* ​[Project DeepSpeech](https://github.com/mozilla/DeepSpeech) - Open source Speech-To-Text engine, using a model trained by machine learning techniques, based on Baidu's Deep Speech research paper.
* ​[Online speech recognition with wav2letter@anywhere (2020)](https://ai.facebook.com/blog/online-speech-recognition-with-wav2letteranywhere/)​
* ​[wav2letter++](https://github.com/facebookresearch/wav2letter) - Fast, open source speech processing toolkit from the Speech team at Facebook AI Research built to facilitate research in end-to-end models for speech recognition.
* ​[Kaldi](https://github.com/kaldi-asr/kaldi) - Speech Recognition Toolkit.
* ​[Building an end-to-end Speech Recognition model in PyTorch](https://www.assemblyai.com/blog/end-to-end-speech-recognition-pytorch) ([HN](https://news.ycombinator.com/item?id=22899107))
* ​[Real-Time Voice Cloning](https://github.com/CorentinJ/Real-Time-Voice-Cloning) - Clone a voice in 5 seconds to generate arbitrary speech in real-time.
* ​[Kaldi Active Grammar](https://github.com/daanzu/kaldi-active-grammar) - Python Kaldi speech recognition with grammars that can be set active/inactive dynamically at decode-time.
* ​[SpecAugment with PyTorch](https://github.com/zcaceres/spec_augment) - PyTorch Implementation of GoogleBrain's SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition.
* ​[Dragonfly](https://github.com/dictation-toolbox/dragonfly) - Speech recognition framework for Python that makes it convenient to create custom commands to use with speech recognition software.
* ​[Gentle](https://github.com/lowerquality/gentle) - Robust yet lenient forced-aligner built on Kaldi. A tool for aligning speech with text.
* ​[Porcupine](https://github.com/Picovoice/porcupine) - On-device wake word detection powered by deep learning.
* ​[Eesen](https://github.com/srvk/eesen) - End-to-End Speech Recognition using Deep RNN Models and WFST-based Decoding.
* ​[Ask HN: Is there any work being done in speech-to-code with deep learning? (2020)](https://news.ycombinator.com/item?id=23497756)​
* ​[Silero Models](https://github.com/snakers4/silero-models) - Pre-trained STT models and benchmarks made embarrassingly simple.
* ​[High-quality pre-trained speech-to-text models now available on Torch Hub](https://pytorch.org/hub/snakers4_silero-models_stt/) ([HN](https://news.ycombinator.com/item?id=24565831))
* ​[Wavenet For Speech Denoising](https://github.com/drethage/speech-denoising-wavenet) - Neural network for end-to-end speech denoising, as described in: "A Wavenet For Speech Denoising".
* ​[Vosk](https://github.com/wzhd/vosk-rs) - Speech recognition toolkit with state-of-the-art accuracy and low latency in Rust.
* ​[Voicegain](https://www.voicegain.ai/) - Speech-to-text Platform and APIs. Speech Recognition.

{% embed url="<https://voice2json.org/>" %}