Hacker News new | ask | show | jobs
by dharma1 3746 days ago
Eesen looks promising, uses LSTM and CTC rather than older tech.

https://github.com/yajiemiao/eesen

Baidu open sourced their CTC implementation

https://github.com/baidu-research/warp-ctc

I think we will have an easy to install OSS speech recognition library and accurate pretrained networks not far off from Google/Alexa/Baidu, running locally rather than in the cloud, within 1-2 years. Can't wait.