generate_scorer_package --lm /mnt/lm/lm.binary --vocab /mnt/lm/vocab-500000.txt --package /mnt/lm/kenlm.scorer --default_alpha 0 --default_beta 0
500000 unique words read from vocabulary file.
Doesn't look like a character based (Bytes Are All You Need) model.
--force_bytes_output_mode was not specified, using value infered from vocabulary contents: false
No --checkpoint path specified, not using bytes output mode, can't continue.
Checkpoint path must contain an alphabet.
Start by creating an alphabet for your models using coqui_stt_training.util.check_characters if needed.
python -m coqui_stt_training.util.check_characters \
--csv-files ... \
--alphabet-format | grep -v '^#' | sort -n > models/alphabet.txt
This will create an alphabet models/alphabet.txt.
Now rerun this script by giving models/ as the checkpoint path.
generate_scorer_package \
--checkpoint models/ \
...
I've updated the code to be more readable and tested it by building generate_scorer_package locally. You can checkout my logs here. I'll merge this PR now as functionally it works as expected. If you want to improve or change the error message let me know.
Addresses https://github.com/coqui-ai/STT/issues/2329
Full logs
EDIT: I changed the message a bit (mainly typos fixes) with this commit https://github.com/coqui-ai/STT/commit/a694187be4817870e53f5e14b24e16b57dfaa581