3.2 Changelog#
3.2.1#
Changed unicode normalization to default to composed forms unless overridden by
--unicode_decomposition true
3.2.0#
Added
--subset_word_count
parameter to Train a new acoustic model (mfa train) to add a minimum word count for an utterance to be included in training subsetsAdded
--minimum_utterance_length
parameter to Train a new acoustic model (mfa train) to add a minimum word count for an utterance to be included in training at allImproved memory usage in compiling training graphs for initial subsets
Add support for transcription via whisperx and speechbrain models
Update text normalization to normalize to decomposed forms
Compatibility with Kalpy 0.6.7