You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Third release, removed dependency from the voice activity detection module, which has been found to not affect performance. The audio file is now segmented in chunks of equal length.
Possible breaks within words are expected to be taken care of in the succeeding iterations.
Released on github now.
Removed the acoustic models from the release file. These are now downloaded from a website.
Updated the README to also include information on how to cope with the possible Audio::Wav warning about ambiguous call to function. A patch is provided to correct Audio::Wav::Read.pm