|
Example Library is obsolete and throws exception on CPU
|
|
2
|
1519
|
August 21, 2018
|
|
OpenNMT to Huggingface Transformers
|
|
2
|
1518
|
December 18, 2023
|
|
In parallel corpus what should I keep, single sentence in each line or paragraph for MT?
|
|
2
|
1519
|
September 19, 2017
|
|
Why do Source tokens/s 1 in every set of iterations?
|
|
3
|
1309
|
June 8, 2017
|
|
Running OpenNMT-tf on Hadoop Cluster
|
|
4
|
1170
|
November 14, 2018
|
|
Increase number of threads using on the fly tokenization
|
|
4
|
1164
|
October 22, 2020
|
|
{‘error’: “Error: ‘TextMultiField’ object has no attribute ‘is_target’”, ‘status’: ‘error’}
|
|
2
|
1502
|
August 13, 2019
|
|
Source features with translate.ua
|
|
2
|
1501
|
August 7, 2017
|
|
Limit GPU memory consumption
|
|
1
|
1839
|
August 25, 2018
|
|
JSON decode error while running server.py
|
|
2
|
1500
|
September 11, 2019
|
|
Sentencepiece decoder working inconsistently
|
|
3
|
1300
|
June 14, 2022
|
|
How to evaluate when using distributed training
|
|
3
|
1298
|
June 3, 2019
|
|
Why exclude last target from inputs?
|
|
1
|
1833
|
May 22, 2018
|
|
CTranslate2 for finetuned model on Nllb-200-distilled-600M with vocabulary expansion
|
|
0
|
2589
|
January 6, 2025
|
|
Multi Label for Synonyms
|
|
3
|
1292
|
March 9, 2020
|
|
Increasing evaluation loss but BLEU score also increasing
|
|
1
|
1824
|
July 19, 2019
|
|
Preprocess.lua on OpenNMT-TF
|
|
1
|
1824
|
May 17, 2018
|
|
Transformer model for OpenNMT Lua version
|
|
1
|
1823
|
August 21, 2018
|
|
Compile Opennmt-Tf models with AWS neuron sdk
|
|
2
|
1488
|
November 26, 2023
|
|
Server for ctranslate2 using OpenNMT-tf models? (not OpenNMT-py)
|
|
2
|
1488
|
November 14, 2021
|
|
Vocabs in preprocess.py
|
|
1
|
1822
|
October 16, 2017
|
|
Shared vocabulary for summarization problem
|
|
1
|
1821
|
October 9, 2017
|
|
Update dropout and label smoothing parameters in training
|
|
1
|
1817
|
November 6, 2019
|
|
Generating learning curves using OpenNMT-py version
|
|
2
|
1483
|
November 21, 2018
|
|
Input type for training
|
|
3
|
1281
|
August 30, 2022
|
|
Long sentences issue in onmt_server
|
|
2
|
1478
|
October 15, 2020
|
|
What are the basic settings for adding linguistic features
|
|
5
|
1045
|
November 19, 2021
|
|
YAML configuration file
|
|
1
|
1809
|
October 12, 2020
|
|
Debugging rest server
|
|
2
|
1476
|
November 16, 2017
|
|
Phi-3-3.8B + Llama2-7B ensemble .... just for fun
|
|
1
|
1018
|
April 24, 2024
|
|
Why my tokenize seem not good
|
|
4
|
1140
|
September 19, 2021
|
|
How can I get perplexity score in a text file?
|
|
3
|
1274
|
December 3, 2019
|
|
Raise error when using python library on ARM
|
|
2
|
1472
|
November 15, 2021
|
|
Beam Search with target words features: how does it work?
|
|
3
|
1270
|
November 21, 2018
|
|
-encoder_type=gnmt
|
|
3
|
1270
|
July 10, 2018
|
|
Words are transformed into numbers. What happens next?
|
|
2
|
1467
|
December 4, 2019
|
|
Changing custon model's hyperparameters via CLI/YAML
|
|
4
|
1135
|
June 12, 2020
|
|
How to support different output vocabulary for different instances?
|
|
3
|
1268
|
January 11, 2020
|
|
Paraphrasing with OpenNMT-tf?
|
|
2
|
1464
|
August 30, 2022
|
|
Error when translate model with nested inputs
|
|
3
|
1263
|
June 4, 2020
|
|
Tranformer: change dropout when finetuning
|
|
4
|
1129
|
September 19, 2021
|
|
How to increase character limit for test sentence?
|
|
1
|
1786
|
November 24, 2017
|
|
Custom spacer in noisy translation
|
|
2
|
1457
|
August 12, 2019
|
|
Minimum Risk Training for NMT
|
|
0
|
2523
|
April 3, 2017
|
|
Difference between GPU and CPU translation
|
|
4
|
1128
|
June 1, 2023
|
|
The training process is hanging
|
|
3
|
1261
|
June 25, 2018
|
|
Lua docker: No value for $TERM
|
|
0
|
2519
|
March 30, 2017
|
|
Small differences in scores between architectures / seed -1
|
|
5
|
1027
|
February 5, 2021
|
|
Question of out of vocabulary words in OpenNMT-py
|
|
1
|
1778
|
May 29, 2018
|
|
Question about parameter, what is "accum_step"
|
|
2
|
1449
|
March 31, 2021
|