|
Using weighted datasets
|
|
5
|
1560
|
February 19, 2021
|
|
Differences between different NMT frameworks
|
|
1
|
2701
|
March 6, 2017
|
|
How does lm score deal with unknown words?
|
|
2
|
2206
|
March 30, 2018
|
|
Copied words in MT
|
|
4
|
1707
|
July 26, 2019
|
|
Model Eng - vietnamese
|
|
3
|
1907
|
August 16, 2021
|
|
Improving word feature labels by block text labeling for context
|
|
2
|
2201
|
July 3, 2017
|
|
CCMatrix: A billion-scale bitext data set for training translation models
|
|
2
|
2201
|
February 12, 2020
|
|
Training on GPU - Cuda Unknown error
|
|
1
|
2694
|
August 23, 2019
|
|
KeyError: 'opt'
|
|
3
|
1904
|
December 3, 2020
|
|
Identical settings for OpenNMT-py and Tensor2Tensor
|
|
3
|
1901
|
May 23, 2018
|
|
CUDA out of memory error
|
|
6
|
1438
|
May 12, 2022
|
|
Slightly different output on localhost vs online
|
|
4
|
1700
|
February 28, 2022
|
|
Issues when exporting to CTranslate2 from a saved model
|
|
3
|
1899
|
March 18, 2021
|
|
Automating hyperparameter optimization
|
|
1
|
2685
|
March 9, 2018
|
|
Data not being Tokenized properly
|
|
4
|
1690
|
May 10, 2020
|
|
Strange learning rate behaviour
|
|
3
|
1885
|
March 25, 2017
|
|
Access the "keys" of data that are in a batch
|
|
4
|
1683
|
November 3, 2017
|
|
Issue in training an end-to-end speech recognition system
|
|
2
|
2169
|
April 4, 2018
|
|
Passing arguments to tf.config?
|
|
2
|
2165
|
June 8, 2018
|
|
What algorithm does Open-NMT-py use?
|
|
2
|
2161
|
March 24, 2021
|
|
Paraphrase generation with OpenNMT
|
|
2
|
2161
|
October 11, 2017
|
|
Not enough memory error in multi-GPU training
|
|
2
|
2161
|
August 1, 2017
|
|
No module named 'onmt' while using embeddings_to_torch.py file
|
|
2
|
2160
|
July 6, 2019
|
|
Speech to text Model training
|
|
4
|
1673
|
October 17, 2019
|
|
How to build the docker image with TensorFlow serving environment and the trained model?
|
|
2
|
2157
|
May 4, 2020
|
|
How to use my finished model.t7 on a website or Discord?
|
|
1
|
2642
|
January 13, 2018
|
|
Reduction in size of checkpoints: `--train_from` arg
|
|
3
|
1867
|
August 12, 2020
|
|
Question Generation using ctranslate2 gpt2 model
|
|
3
|
1863
|
March 9, 2023
|
|
Corpus level TER averaging
|
|
2
|
2151
|
November 8, 2017
|
|
Different subword tokenization in same word pattern
|
|
3
|
1863
|
November 20, 2020
|
|
BLEU score of word features model is lower than Base model
|
|
3
|
1860
|
April 21, 2020
|
|
What is the Kaldi input format? Where can I find an example or definition?
|
|
3
|
1859
|
June 1, 2017
|
|
Word embeddings sizes
|
|
4
|
1662
|
February 27, 2019
|
|
Variable Dropout setting
|
|
3
|
1857
|
January 17, 2017
|
|
Extract / Dissect / Freeze Transformer's Encoder Decoder Components
|
|
3
|
1856
|
June 7, 2024
|
|
TensorFlow NMT output form French to Englis translation not improving even after 165000 training steps
|
|
4
|
1660
|
May 14, 2018
|
|
Bi-Directional Bottom Encoder
|
|
6
|
1400
|
May 7, 2021
|
|
Opennmt-py training speed
|
|
2
|
2138
|
May 19, 2021
|
|
Embedding Training on Transformer
|
|
3
|
1846
|
August 18, 2020
|
|
Build custom Dataset for a custom language
|
|
3
|
1844
|
November 3, 2022
|
|
Recommended training time, and how to tokenize
|
|
3
|
1840
|
November 6, 2020
|
|
CUDA out of memory in validation step
|
|
3
|
1841
|
May 6, 2019
|
|
Retrain and translate "at the same time"
|
|
4
|
1640
|
July 30, 2019
|
|
Retraining a pretrained model in OpenNMT-py
|
|
2
|
2116
|
October 29, 2019
|
|
OpenNMT-tf Distributed Training - Processes don't end after training completes
|
|
4
|
1638
|
November 29, 2018
|
|
How to improve the accuracy of model?
|
|
1
|
2581
|
July 23, 2018
|
|
Problems in training train.py
|
|
1
|
2580
|
August 8, 2017
|
|
Add support for distributed training on multiple CPU only nodes
|
|
1
|
2580
|
June 28, 2017
|
|
Alignment not coming properly
|
|
1
|
1450
|
November 30, 2018
|
|
Different Bleu Score Results
|
|
1
|
2575
|
November 27, 2019
|