Modeling pronunciation probabilities¶
MFA includes a utility command for training pronunciation probabilities of a dictionary given a corpus for alignment.
The resulting dictionary can then be used as a dictionary for alignment or transcription.
Steps to train:
- Provided the steps in Installation have been completed and you are in the same Conda/virtual environment that MFA was installed in.
- Run the following command, substituting the arguments with your own paths:
mfa train_dictionary corpus_directory dictionary_path acoustic_model_path output_dictionary_path
acoustic_model_path can also be a language that has been pretrained by MFA developers. For instance, to use
the pretrained English model, first download it via
mfa download acoustic english. A list of available
acoustic models will be provided if you run
mfa download acoustic. See Pretrained models for more details.
Path to a YAML config file that will specify either the alignment options or the training configuration. See Configuration for more details.
Number of characters to use to identify speakers; if not specified, the aligner assumes that the directory name is the identifier for the speaker. Additionally, it accepts the value
prosodylabto use the second field of a
_delimited file name, following the convention of labelling production data in the ProsodyLab at McGill.
Temporary directory root to use for aligning, default is
Number of jobs to use; defaults to 3, set higher if you have more processors available and would like to align faster