OpenNMT Forum

Question about using the Pretrained embedding [Support] (4)
"Import pyonmttok" failed & "pip install pyonmttok" faileld - Windows 10 [Support] (2)
Low ressource languages, infinite training, and back-translation [Research] (4)
Receiving a "ValueError: best_eval_result cannot be empty or no loss is found in it." while training the transformer model [Support] (3)
Can I use trained modules to creat a translation server? [Tutorials] (3)
OpenNMT-tf Fine tuning base model gives worse and decreases BLEU scores [Support] (9)
Handle numbers, urls, dates [Support] (3)
TransformerBig model - GTX 1080 Ti (11G) - ResourceExhaustedError [Support] (9)
Use GloVe with concatenated word features (OpenNMT-py) [Support] (1)
Tokenization OpenNMT-tf [Support] (4)
Using multiple gpus in training.py [Support] (5)
Translation server in OpenNMT-tf [Support] (3)
Perplexity in opennmt-tf [Support] (2)
Alignment not coming properly [Support] (2)
OpenNMT-tf Distributed Training - Processes don't end after training completes [Support] (5)
OpenNMT-tf serving with latest prediction_service_pb2_grpc for translation [Support] (3)
What is the relationship between ppl, accuracy and bleu scores in machine translation? In my experiment, although ppl and accuracy on the validationset are greatly improved, Bleu scores is reduced [Research] (1)
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 [Support] (5)
OpenNMT-tf toy-ende model scoring and inference clarification [Support] (3)
Issues when running the English-German WMT15 training ( 2 ) [Support] (23)
Issue in using distributed training in openNMT-TF ( 2 ) [Support] (32)
Beam Search with target words features: how does it work? [Support] (4)
Generating learning curves using OpenNMT-py version [Support] (3)
Opnenmt-th takes so long to load training data before it really starts the training process [Support] (3)
Learning rate reduced to 0 after start_decay_steps values [Support] (4)
Poor translation result with English->German and German->English pre-trained models [Support] (7)
Questions on large batch size training with Transformer in low-resource scenario [Research] (3)
I have question about the transformer in SubLayerConnection, is the code wrong? [Development] (3)
How to change the data parallelism to model parallelsim? [Support] (3)
Basic Default Training Parameters for Language Translation [Tutorials] (2)