How long should the training with the default data take? (8)
Incorporating translation dictionary during decoding (11)
Is there any method to force loading the full dataset into memroy instead of lazily load in OpenNMT-py? (1)
-phrase_table option ( 2 ) (30)
Training multiple shards not working for the pytorch version? (3)
Two short questions on training (2)
Where to define other plots for tensorboard? (2)
Preprocess with -dynamic_dict does not create a valid data file? (2)
Horrible results with beam width and replace_unk (5)
Problem with incremental/in-domain training ( 2 ) (35)
Multi way training (4)
Hi , I have 130k train src tgt pairs, but the log info of training process shows that there are only 22k train pairs after we preprocess the data (4)
Incremental training and unk symbols ssiue (2)
Using pretrained En-De model? (2)
Error using OpenNMT-py (Multiple edits, new issue) (1)
Assertion `srcIndex < srcSelectDimSize` failed (1)
Remove words from vocabularies (1)
Where do I get/do you get training data? (6)
Specifying input feed required to use global attention? (3)
Re-training Existing Model with Monolingual Corpora (8)
Translate using pre-trained English -> German model in pyTorch (4)
Limit GPU memory consumption (2)
Need Help regarding Data Preparation (3)
How can I use embeddings? (5)
Improvement of BLEU Scores (2)
Example Library is obsolete and throws exception on CPU (3)
Training LM with monolingual corpora (6)
Bad results from DE-EN Pretrained models (10)
AttributeError: 'DeprecateAction' object has no attribute 'mdhelp' (1) error: unrecognized arguments: -phrase_table data/phrase_table.txt (2)