MFA Validate Inconsistent Output

[shreeshailgan]

I am running mfa validate on the LibriTTS-train-clean-460 dataset using an IPA dictionary I have. The output contains:

WARNING  288196total OOV tokens       

However, in the generated oov_counts.txt file that is generated (see snapshot below), the sum of the counts in the 2nd column is 32,905. Shouldn't these two numbers be equal? If not, what does 288,196 represent?

--and   151
phoenix 104
--the   99
--a 88
--i 77
--but   67
ion 65
...

[mmcauliffe]

Are you passing configuration options that remove punctuation symbols? What's the full command you're running and what version are you on?

[shreeshailgan]

MFA version montreal-forced-aligner 3.0.1 pyhd8ed1ab_0 conda-forge

Full command mfa validate /path/to/data/ /path/to/lexicon --ignore_acoustics --num_jobs 48