Wav2letter: Automatic Speech Recognition Toolkit from Facebook AI Research

Suggestion for anyone interested in this.

I recommend not copying and pasting the blocks of code into your terminal. Look at the install commands first and make sure you are running them from the preferred root directory.

Can anyone suggest some good resources for a beginner to get to speed on Speech Recognition and synthesis?

I guess it depends on what exactly you want to do. If you want to get familiar with the components of a speech recognition system at the level of fiddling with a bunch of shell scripts until you have an end-to-end pipeline from recording speech samples to recognizing new speech, I can recommend the "Kaldi for Dummies" tutorial. [1] It helped me a lot to get an appreciation for the steps that go into making such a system work.

[1] http://kaldi-asr.org/doc/kaldi_for_dummies.html

the link for torch is borkened

Submit a pull request - the URL just needs those colons