All commands#
The mfa
command line utility has several subcommands, which are listed below grouped by general domain.
Preparation#
Command |
Description |
Link |
---|---|---|
|
Validate a corpus |
Forced Alignment#
Command |
Description |
Link |
---|---|---|
|
Perform forced alignment with a pretrained model |
|
|
Train an acoustic model and export resulting alignment |
|
|
Adapt a pretrained acoustic model on a new dataset |
|
|
Estimate pronunciation probabilities from aligning a corpus |
Corpus creation#
Command |
Description |
Link |
---|---|---|
|
Use voice activity detection to create segments |
|
|
Train an ivector extractor for speaker classification |
|
|
Use ivector extractor to classify files or cluster them |
|
|
Generate transcriptions using an acoustic model, dictionary, and language model |
|
|
Train a language model from a text corpus or from an existing language model |
|
|
Run the Anchor annotator utility (if installed) for editing and managing corpora |
Other utilities#
Command |
Description |
Link |
---|---|---|
|
Inspect/list/download/save models |
|
|
Configure MFA to use customized defaults for command line arguments |
|
|
List previous MFA commands run locally |
Grapheme-to-phoneme#
Command |
Description |
Link |
---|---|---|
|
Use a G2P model to generate a pronunciation dictionary |
|
|
Train a G2P model from a pronunciation dictionary |