News for hackers. Stuff that matters.

A comment on Reaching new records in speech recognition.

Re:Reaching new records in speech recognition by earthtolazlo on Saturday March 11, 2017 @02:09PM (#13846671)
It would be great to see one of these frameworks offered as an offline solution. Right now the only options are WSR/Sphinx4, which have significant accuracy issues, and Nuance's products, which are extremely unfriendly to developers.
[ Parent | on HN ]
Re:Reaching new records in speech recognition by braindead_in on Saturday March 11, 2017 @02:44PM (#13846834)
Mozilla's DeepSpeech has a native client https://github.com/mozilla/DeepSpeech
[ Parent | on HN ]
Re:Reaching new records in speech recognition by findateamfirst on Saturday March 11, 2017 @03:04PM (#13846941)
Kaldi is state of the art. A bit harder to use admittedly.
[ Parent | on HN ]