Problem when run bitextor using document aligner NMT

[lumosnysm]

I run bitextor with config just like the documentation

...
initCorpusTrainPrefix: ['/home/user/Europarl.en-fr.train']
initCorpusDevPrefix: ['/home/user/Europarl.en-fr.dev']
initCorpusTestPrefix: ['/home/user/Europarl.en-fr.test']

marianDir: /home/user/marian-dev
mosesDir: /home/user/mosesdecoder
subwordNmtDir: /home/user/subword-nmt

nmtVocabSize: 50000

LANG2Detokenizer: "/home/user/mosesdecoder/scripts/tokenizer/detokenizer.perl -l fr"

gpuId: 0

marianArgs: [" --optimizer-delay 1", "--mini-batch-fit", "--mini-batch 1000", "--maxi-batch 1000", "--overwrite", "--keep-best", "--valid-metrics perplexity", "--valid-log valid.log", "--log train.log", "--dropout-rnn 0.2", "--dropout-src 0.2", "--dropout-trg 0.2 ", "--cost-type ce-mean-words", "--layer-normalization", "--exponential-smoothing", "--tied-embeddings", "--valid-metrics bleu"]
...

but it throwing this error

KeyError in line 23 of /workspace/thviet/bitextor/snakemake/nmt/Snakefile:
'LANG1Tokenizer'
  File "/workspace/thviet/bitextor/snakemake/nmt/Snakefile", line 23, in <module>

Can you help me to fix this?, thank you.

[lpla]

Hi. Which version of Bitextor are you using?

[lumosnysm]

@lpla I am using the master branch of this repo.

[lpla]

It is a bug. Just pushed a workaround to master. Pull these changes and try to run Bitextor again. Let me know if this works or not, as I couldn't test it (I don't have a Marian environment with GPU available right now).

Thank you for reporting!

[lumosnysm]

@lpla thanks for your quick support
Do i need to set the marianModelFile in the config file as i don't see it in the documentation
I got this error

KeyError in line 98 of /workspace/thviet/bitextor/snakemake/nmt/Snakefile:
'marianModelFile'
  File "/workspace/thviet/bitextor/snakemake/nmt/Snakefile", line 98, in <module>

[lpla]

Yes. We forgot to add that one to the README.md. Thank you for reporting it!

[lpla]

Hi. We decided to remove MarianNMT training settings and code from our last push to master towards Bitextor 8.0 release, as it is deprecated. If you want to keep using it, you will need to use Bitextor 7.x code. Closing issue.