Michael McAuliffe
Michael McAuliffe
Hello, @h-vetinari and I got Kaldi building successfully on conda forge earlier this year, so I think it should be possible to get pykaldi on there as well built against...
Hello, I'm the maintainer for the [Montreal Forced Aligner (MFA)](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) and currently working on a new Japanese model for speech-to-text alignment. My current prototype uses sudachipy to generate morphemes, post-process...
To resolve https://github.com/MontrealCorpusTools/ISCAN/issues/245, have pause encoding also tag any contained syllables/phones/etc as `:pause` rather `:speech`.
One inefficiency in querying is getting a transcript of utterances, due to the memory requirements of querying lower annotations. In the process of encoding, the transcript could be saved relatively...
This manifests as only having a single speaker, which may cause issues with memory if there are in fact many speakers, and many/all corpora will have multiple speakers.
The query modules are a bit messy and could use cleaning up/refactoring, with some overlapping methods, inconsistent naming schemes from various additions of code and general lack of clarity in...
Finish comprehensive pass over enrichment functionality in PolyglotDB.
Check and make sure every part of the Polyglot API is documented. For each instance, it should be in the user documentation if the function/class is forward facing and intended...
The goal is to create subannotations in PolyglotDB using a Praat script that measures voicing during a phone segment. - [ ] Praat script that gets voicing values - [...
Call back functions should always return: - Description of current state - Percent of overall progress - Estimation of remaining time