News#
Roadmap#
Warning
Please bear in mind that all plans below are tentative and subject to change.
Version 5.0 (Planned for 2027)#
Removal of legacy alignment commands
Legacy models can still be used with previous versions of MFA
Support for neural network acoustic models
Version 4.0 (Planned for end of 2026)#
Deprecation of legacy model usage
Commands for align_hf, adapt_hf, and Align a single file with Hugging Face model (mfa align_one_hf) will be renamed to align, adapt, and Align a single file (mfa align_one) and 3.4 align, adapt, and Align a single file (mfa align_one) will be renamed align_legacy, adapt_legacy, and align_one_legacy
Refactor and code clean up
Broad phone sets with modular implementation of phonological rules
Richer lexicon support