|
Raising training speed without comprimising too much on quality
|
|
7
|
2099
|
December 4, 2017
|
|
Error with latest CTranslate2 version in OpenNMT-py REST server
|
|
3
|
2964
|
July 5, 2021
|
|
Could I submit pull request to tokenization hook for Korean and Japanese?
|
|
3
|
1666
|
May 23, 2018
|
|
Visualizing the graph
|
|
7
|
2085
|
June 16, 2020
|
|
Reproducing pre-trained Transformer model
|
|
8
|
1967
|
April 16, 2020
|
|
Combined embeddings as inputs
|
|
6
|
2227
|
April 22, 2019
|
|
"-add_tokenized_output "option in rest_translation_server.lua
|
|
8
|
1967
|
May 10, 2018
|
|
About input_feed
|
|
6
|
2226
|
July 14, 2017
|
|
World_size 2 and gpu-ranks 0 1 lead to two GPU processes per GPU
|
|
4
|
2632
|
July 24, 2020
|
|
Improving the gpuid option
|
|
4
|
2626
|
January 18, 2017
|
|
How to coordinate GPU memory usage
|
|
5
|
2398
|
November 20, 2017
|
|
What's wrong with my train.py?
|
|
5
|
2384
|
December 20, 2017
|
|
How long to train a model without overfitting?
|
|
2
|
3364
|
December 30, 2018
|
|
Running OpenNMT on Windows - AttributeError: ‘Namespace’ object has no attribute ‘fix_word_vecs_enc’
|
|
1
|
4114
|
September 3, 2021
|
|
Inferencing with translate.py
|
|
6
|
2201
|
March 9, 2022
|
|
Praticality of CPU training
|
|
2
|
3359
|
January 22, 2017
|
|
GitHub - dothq/translate: 🌐 Translation microservice powered by OpenNMT
|
|
0
|
1035
|
November 30, 2021
|
|
Internal type error when using trained model
|
|
5
|
2367
|
August 15, 2017
|
|
Training speed with alignment significantly drops down
|
|
0
|
1034
|
January 11, 2024
|
|
Perplexity nan at epoch 5
|
|
3
|
2894
|
October 12, 2017
|
|
Text Summarization
|
|
1
|
4087
|
July 21, 2017
|
|
Validating trained model
|
|
6
|
2183
|
May 16, 2017
|
|
Change opus format to be similar to toy dataset
|
|
0
|
1029
|
November 1, 2022
|
|
RuntimeError: Unsupported model binary version with ctranslate2
|
|
2
|
3323
|
May 18, 2022
|
|
Help applying changes made to the c++ model
|
|
6
|
2175
|
February 13, 2023
|
|
Tracking Training progress
|
|
1
|
1289
|
December 20, 2021
|
|
Domain Specific Training Questions (Transfer Learning?)
|
|
2
|
3320
|
April 4, 2020
|
|
Number of samples in one training step together with accumulation
|
|
6
|
2169
|
April 8, 2021
|
|
Pretrained embedding for OpenNMT-py : No module named 'onmt'
|
|
2
|
3304
|
May 15, 2019
|
|
Assert model_dim % head_count == 0
|
|
1
|
1284
|
November 8, 2022
|
|
Ctranslate2 on Raspberry 32bit
|
|
8
|
1907
|
March 30, 2021
|
|
Fix_word_vecs option stored in the model?
|
|
4
|
2557
|
April 3, 2017
|
|
Command errored out with exit status 128: git clone
|
|
0
|
5696
|
January 20, 2020
|
|
Slow convergence on training a transformer model for Italian-English
|
|
2
|
3288
|
August 5, 2019
|
|
If there is any way to keep placeholders as same as source when call NMT
|
|
1
|
4023
|
June 6, 2017
|
|
Error installing openNMT-tf in Linux
|
|
6
|
2153
|
August 13, 2018
|
|
Text Summarization Question?
|
|
3
|
2838
|
May 2, 2017
|
|
NMT's vocabulary
|
|
2
|
3270
|
February 7, 2018
|
|
Inference latency comparison with fastertransformer
|
|
2
|
3263
|
October 20, 2021
|
|
Guided alignment with multi-source
|
|
6
|
2133
|
November 27, 2020
|
|
How do you use '-replace_unk' on server.py? (TranslationServer.py)
|
|
2
|
1833
|
May 30, 2019
|
|
How to use Bert embedding into OpenNMT seq2seq model
|
|
4
|
2519
|
May 11, 2021
|
|
Cuda OOM for Validation
|
|
8
|
1877
|
December 17, 2018
|
|
Error when running translate.py
|
|
3
|
2808
|
June 29, 2018
|
|
Paragraph vs sentence segmentation
|
|
2
|
3234
|
October 16, 2017
|
|
M2m100 sentences cut off during translation
|
|
2
|
3232
|
March 16, 2022
|
|
Translate so slow
|
|
4
|
2500
|
July 6, 2021
|
|
Pre-train encoder side UTF-16 word embeddings in OpenNMT-py?
|
|
0
|
996
|
August 2, 2018
|
|
Conv1D on GPU currently requires the cuDNN library which is not integrated in this build
|
|
3
|
2782
|
February 12, 2023
|
|
Different RNN architecture for each layer of Encoder
|
|
2
|
3211
|
June 8, 2017
|