Add word timings, IPA syllables, confusion network to speech reco response
I know you have this information available in the speech decoder; can you please expose it via the public API?
- The list of phrase elements (words) and their timestamps within the audio stream
- IPA phonemes for each phrase element
- Confusion network output from the lattice
Right now I am forced to reconstruct / approximate this data after the fact and it would be 1000x easier if the API could just give it to me.