|
External reward signal for human-in-the-loop training
|
|
2
|
1849
|
January 20, 2017
|
|
OpenNMT-py Server + CTranslate2 target_prefix support?
|
|
2
|
1845
|
April 23, 2022
|
|
Why NLL loss is not normalized by the number of tokens?
|
|
1
|
2256
|
September 22, 2019
|
|
Error after evaluation with FP16
|
|
3
|
1594
|
February 11, 2019
|
|
What are the basic settings for adding linguistic features
|
|
5
|
1303
|
November 19, 2021
|
|
"unknown" words with BPE tokenization
|
|
1
|
2253
|
February 20, 2017
|
|
Small differences in scores between architectures / seed -1
|
|
5
|
1297
|
February 5, 2021
|
|
Translation outputs sentences with repeated phrases
|
|
2
|
1830
|
December 17, 2019
|
|
Where can I find sota BLEU scores results for various language pairs?
|
|
2
|
1827
|
April 11, 2019
|
|
Error in Writing model during runtime saving checkpoint
|
|
3
|
1580
|
June 16, 2017
|
|
With adding "--save_config" argument, onmt_train cannot continue--what's wrong and how to solve this?
|
|
4
|
1413
|
June 21, 2020
|
|
About onmt.utils.loss
|
|
1
|
2232
|
April 23, 2022
|
|
Phi-3-3.8B + Llama2-7B ensemble .... just for fun
|
|
1
|
1262
|
April 24, 2024
|
|
Why is <UNK> in GOLD?
|
|
2
|
1816
|
March 14, 2020
|
|
Run time problem running with PyTorch 1.3 under Windows 10
|
|
3
|
1572
|
January 17, 2020
|
|
Recording of Paris meetup 2nd-3rd March 2018
|
|
2
|
1815
|
December 3, 2019
|
|
OpenNMT-py models output
|
|
2
|
1812
|
February 25, 2019
|
|
PC Specs for a NMT | How much RAM?
|
|
2
|
1812
|
January 16, 2017
|
|
CTranslate2 for finetuned model on Nllb-200-distilled-600M with vocabulary expansion
|
|
0
|
3141
|
January 6, 2025
|
|
Resource exhausted error
|
|
3
|
1568
|
May 20, 2019
|
|
Unnecessary words from translate
|
|
3
|
1568
|
December 14, 2017
|
|
Generative Adversarial Network for NMT
|
|
3
|
1566
|
December 1, 2019
|
|
Domain Adaptation
|
|
3
|
1565
|
October 1, 2021
|
|
Difference between GPU and CPU translation
|
|
4
|
1398
|
June 1, 2023
|
|
Why my tokenize seem not good
|
|
4
|
1397
|
September 19, 2021
|
|
Paraphrasing with OpenNMT-tf?
|
|
2
|
1801
|
August 30, 2022
|
|
How to evaluate when using distributed training
|
|
3
|
1559
|
June 3, 2019
|
|
Overfitting Model
|
|
2
|
1800
|
February 28, 2022
|
|
Running OpenNMT-tf on Hadoop Cluster
|
|
4
|
1395
|
November 14, 2018
|
|
Correct pipeline for NMT using BPEmb
|
|
3
|
1558
|
June 18, 2020
|
|
Reset learning rate after update-vocabulary
|
|
2
|
1799
|
May 13, 2019
|
|
How to load pretrained word2vec embedding files with opennmt-tf?
|
|
1
|
2200
|
January 2, 2019
|
|
Will pay $1000 for someone to help build a Spanish to English text translator
|
|
1
|
2199
|
May 21, 2019
|
|
Increase number of threads using on the fly tokenization
|
|
4
|
1390
|
October 22, 2020
|
|
Why do Source tokens/s 1 in every set of iterations?
|
|
3
|
1556
|
June 8, 2017
|
|
Early_stopping in openNMT-py
|
|
2
|
1793
|
September 2, 2020
|
|
How to train custom model?
|
|
1
|
2195
|
December 10, 2019
|
|
Training Server Docker
|
|
2
|
1790
|
April 26, 2022
|
|
Can we use language translation model for Hindi to English translation?
|
|
1
|
2189
|
June 27, 2017
|
|
Visualisation During Training
|
|
2
|
1786
|
October 1, 2021
|
|
Changing custon model's hyperparameters via CLI/YAML
|
|
4
|
1382
|
June 12, 2020
|
|
Multi Label for Synonyms
|
|
3
|
1545
|
March 9, 2020
|
|
Sentencepiece decoder working inconsistently
|
|
3
|
1543
|
June 14, 2022
|
|
Improve my translation score
|
|
4
|
1381
|
August 31, 2021
|
|
Cannot find any OpenNMT AMI on EC2
|
|
4
|
1380
|
September 14, 2018
|
|
Input type for training
|
|
3
|
1541
|
August 30, 2022
|
|
Does word embedding size change when we use word features?
|
|
3
|
1540
|
May 29, 2019
|
|
Output from CTranslate and OpenNMT translate differ
|
|
2
|
1775
|
May 14, 2017
|
|
Translation_server.lua exchange trouble after a reboot
|
|
3
|
1536
|
April 28, 2017
|
|
OpenNMT to Huggingface Transformers
|
|
2
|
1772
|
December 18, 2023
|