Training an ivector extractor¶
The Montreal Forced Aligner can train ivector extractors using an acoustic model for generating alignments. As part of this training process, a classifier is built in that can be used as part of Speaker classification.
Steps to train ivector extractor:
- 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_ivector corpus_directory dictionary_path acoustic_model_path output_model_path
Path to a YAML config file that will specify the training configuration. See Ivector 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 process faster