|
Using OpenNMT for Information Retrieval
|
|
3
|
1648
|
May 27, 2018
|
|
OpenNMT-py models stops making training progress while trying to validate
|
|
7
|
2068
|
February 26, 2021
|
|
Bi-directional language model
|
|
3
|
2917
|
April 10, 2018
|
|
Sentence piece in OpenNMT-py
|
|
3
|
2917
|
June 28, 2019
|
|
ONMT net structure?
|
|
5
|
2378
|
May 11, 2018
|
|
Weight table:set weight of some vocabulary
|
|
5
|
2374
|
May 15, 2017
|
|
Does continuing training start from unseen/less-seen data?
|
|
5
|
2371
|
February 22, 2021
|
|
Integrating ctranslate2 with Unreal Engine
|
|
0
|
1032
|
September 23, 2024
|
|
Decreasing run time
|
|
2
|
1884
|
April 25, 2021
|
|
Re-training Existing Model with Monolingual Corpora
|
|
7
|
2042
|
August 29, 2018
|
|
Words are lost when transforme long sentences
|
|
5
|
2357
|
October 22, 2020
|
|
Large perplexity
|
|
6
|
2181
|
December 12, 2018
|
|
Training crash at validation
|
|
4
|
2579
|
July 1, 2021
|
|
Transformer OpenNMT-py standard hyperparameters + pretrained model
|
|
4
|
2580
|
February 14, 2019
|
|
OpenNMT-py doubts
|
|
5
|
2348
|
January 1, 2018
|
|
About mask in attention layer and decoder
|
|
4
|
2558
|
September 12, 2017
|
|
Automatic post-edit training of a training
|
|
5
|
2336
|
June 14, 2018
|
|
Predictive translation server
|
|
4
|
2553
|
August 29, 2017
|
|
How using parameter byte_fallback with opennmt-tokenizer
|
|
1
|
4006
|
January 13, 2025
|
|
BPE and other tokenization options with rest_translation_server.lua
|
|
5
|
2311
|
January 2, 2018
|
|
Translate_batch(): incompatible function arguments. for ctranslate2
|
|
1
|
4004
|
January 18, 2023
|
|
Indigenous languages: first try with Palikúr - looking for advices
|
|
2
|
1031
|
April 21, 2019
|
|
OpenNMT-tf Fine tuning base model gives worse and decreases BLEU scores
|
|
8
|
1879
|
December 5, 2018
|
|
Is it normal to see "Weighted corpora loaded so far" in a loop during the finetuning phase on a very small dataset?
|
|
6
|
2129
|
February 15, 2024
|
|
Difference between bpe and character-level tokenization for BLUE score
|
|
2
|
3242
|
December 15, 2019
|
|
OpenNMT translate string as an input
|
|
4
|
2502
|
October 12, 2018
|
|
Improving the gpuid option
|
|
4
|
2501
|
January 18, 2017
|
|
MS Azure image?
|
|
1
|
1248
|
March 9, 2017
|
|
SentencePiece: Understanding pre-tokenization on raw Unicode bytes?
|
|
2
|
3221
|
August 26, 2020
|
|
How long to train a model without overfitting?
|
|
2
|
3218
|
December 30, 2018
|
|
Praticality of CPU training
|
|
2
|
3217
|
January 22, 2017
|
|
Error whey saving vocab file in openmt-py
|
|
1
|
1244
|
January 25, 2021
|
|
Raising training speed without comprimising too much on quality
|
|
7
|
1962
|
December 4, 2017
|
|
What's wrong with my train.py?
|
|
5
|
2262
|
December 20, 2017
|
|
Combined embeddings as inputs
|
|
6
|
2094
|
April 22, 2019
|
|
AttributeError: 'SequenceRecordInputter' object has no attribute 'input_depth'
|
|
5
|
2257
|
March 22, 2019
|
|
Linker error when compiling CTranslate2 with "-march=corei7-avx" (CXX_FLAGS)
|
|
6
|
2090
|
September 12, 2020
|
|
Wrong word UNK replacement
|
|
7
|
1951
|
October 15, 2019
|
|
Tokenizer v1.20.0 with SentencePiece v0.1.92 potentially problematic?
|
|
5
|
2252
|
October 3, 2020
|
|
OpenNMT-py installation in Google Colab
|
|
2
|
3182
|
April 30, 2020
|
|
Perplexity nan at epoch 5
|
|
3
|
2756
|
October 12, 2017
|
|
How should I clean the texts before training?
|
|
4
|
2466
|
February 11, 2020
|
|
Multimodal feature input for seq2seq
|
|
7
|
1947
|
August 11, 2021
|
|
Internal type error when using trained model
|
|
5
|
2246
|
August 15, 2017
|
|
Text Summarization
|
|
1
|
3887
|
July 21, 2017
|
|
Could I submit pull request to tokenization hook for Korean and Japanese?
|
|
3
|
1545
|
May 23, 2018
|
|
The difference between parameter
|
|
8
|
1832
|
January 4, 2017
|
|
About input_feed
|
|
6
|
2075
|
July 14, 2017
|
|
Pretrained embedding for OpenNMT-py : No module named 'onmt'
|
|
2
|
3168
|
May 15, 2019
|
|
Command errored out with exit status 128: git clone
|
|
0
|
5481
|
January 20, 2020
|