李明伟

problem： 1.Not translated 2.Duplicate text 3.Missing words thanks

@guillaumekln yeah， about 4 million。I have used the Mecab tool to do the tokenize

@guillaumekln ,sorry, I forgot. it have 400W line。The command para:-layers 3 -rnn_size 500

hi @guillaumekln Yes, When I translate a length of a sentence, I always omit some content.

Hi @guillaumekln Can I turn off the caching mechanism? We have a lot of request connections. Frequent cases of low memory.   Now I'm in a situation where the...

Hi @guillaumekln , I shouldn't have set it up. Excuse me, how should I do it?

It doesn't look like it has any effect. @guillaumekln

Hi @francoishernandez It's like a set of numbers in the picture below. In the opennmt-lua version, it can get it with -withAttn 

Hi snukky, Thank you for your support. `./build/marian --train-sets /Marian/1_ForTrain/TagRemoved_Source_Train_2560035.tok.en /Marian/1_ForTrain/TagRemoved_Target_Train_2560035.tok.de --vocabs /Marian/source_vocab.yml /Marian/target_vocab.yml --model /Marian/pre-train_model.npz --devices 0 --dim-emb 500 --after-epochs 13 --max-length 70 --max-length-crop` The training file has 2560035...

HI emjotde, I build the vocabularies with the /build/marian-vocab command. Commas and periods don't do word breaks.