|
Cannot scale well with multiple GPUs
|
|
32
|
5266
|
November 8, 2022
|
|
First OpenNMT Workshop in Paris - Registration is open!
|
|
13
|
4384
|
March 1, 2018
|
|
OpenNMT-py BERT Tutorial
|
|
13
|
7678
|
October 13, 2021
|
|
Pre-processing corpora
|
|
23
|
5826
|
December 12, 2017
|
|
Best way to handle emojis during translation
|
|
37
|
4429
|
June 3, 2020
|
|
Training stuck (multi GPU, transformer)
|
|
12
|
7492
|
June 1, 2024
|
|
Load a savedmodel in tensorFlow
|
|
18
|
6175
|
April 12, 2022
|
|
Translation server crashing after initialization
|
|
31
|
4720
|
March 7, 2017
|
|
Bpe, vocab size
|
|
20
|
5745
|
August 3, 2021
|
|
Linguistic features surprisingly decrease the performance!
|
|
19
|
5830
|
May 14, 2019
|
|
Are you interested in training Russian-Abkhazian parallel corpus?
|
|
29
|
4727
|
June 9, 2020
|
|
Tokenize.lua results in
|
|
16
|
6260
|
June 23, 2017
|
|
Epochs Determination
|
|
21
|
5408
|
April 2, 2024
|
|
CTranslate2 on OpenNMT-py Server
|
|
13
|
3793
|
February 1, 2021
|
|
Multi-GPUs is slower than single GPU
|
|
12
|
6972
|
April 16, 2019
|
|
Issues when running the English-German WMT15 training
|
|
22
|
5191
|
November 22, 2018
|
|
Sentence length & translation quality
|
|
13
|
6558
|
June 11, 2018
|
|
Improvement of performance by data normalization
|
|
23
|
4792
|
August 16, 2019
|
|
Ensemble decoding
|
|
16
|
5655
|
October 19, 2017
|
|
Convert M2M model to CTranslate2
|
|
12
|
6412
|
June 20, 2022
|
|
In-domain training
|
|
14
|
3301
|
March 19, 2017
|
|
Translate with CTranslate using cuda
|
|
16
|
5429
|
November 25, 2020
|
|
OpenNMT-py error when training with large amount of data
|
|
21
|
4742
|
November 6, 2022
|
|
Supporting Tokenize/Detokenize automatically by Translation Server
|
|
17
|
5067
|
September 11, 2017
|
|
Some experience when training with large datasets
|
|
17
|
5023
|
November 1, 2017
|
|
Leave Unknown Words Untranslated
|
|
17
|
5000
|
December 19, 2019
|
|
Pretrained Model English<->German
|
|
13
|
3180
|
February 14, 2017
|
|
How to resume training from last interupted state
|
|
11
|
3407
|
July 21, 2019
|
|
Terminology handling
|
|
16
|
4961
|
September 8, 2023
|
|
Bleu score falling when detokenizing, detruecasing and de subword BPE
|
|
16
|
4828
|
March 23, 2023
|
|
Where can I find sentencepiece_model of my model?
|
|
12
|
5380
|
January 29, 2020
|
|
Single character tokenization?
|
|
10
|
5750
|
August 26, 2021
|
|
Issue in using distributed training in openNMT-TF
|
|
31
|
3302
|
November 21, 2018
|
|
Installed but can't get pre-processing working
|
|
16
|
4450
|
November 25, 2019
|
|
Korean - English Model
|
|
14
|
4696
|
May 25, 2020
|
|
DataLossError : Checksum does not match
|
|
10
|
5425
|
May 18, 2019
|
|
TensorFlow REST API + SentencePiece
|
|
19
|
4008
|
August 30, 2021
|
|
Size of feature embeddings (and some digression about casing methods)
|
|
17
|
4182
|
July 29, 2020
|
|
Preprocessing corpus for case_feature and POS tags
|
|
12
|
4864
|
March 22, 2018
|
|
Fine tuning nllb-200-distilled-600M model
|
|
16
|
4233
|
April 15, 2024
|
|
XML tags handling
|
|
18
|
3948
|
October 23, 2018
|
|
Teacher forcing
|
|
11
|
4911
|
July 25, 2017
|
|
RuntimeError: Model diverged with loss = NaN
|
|
13
|
4432
|
February 21, 2020
|
|
Training Won't resume from latest checkpoint
|
|
14
|
4082
|
September 4, 2022
|
|
Detokenization clarification
|
|
10
|
4739
|
January 11, 2017
|
|
Convert to Keras Model for CoreMlTools
|
|
16
|
3671
|
June 4, 2021
|
|
Custom attention mask
|
|
20
|
3236
|
August 18, 2020
|
|
Feature Request List
|
|
14
|
3811
|
August 7, 2018
|
|
End and Start Tokens
|
|
11
|
4143
|
November 29, 2021
|
|
Incorporating translation dictionary during decoding
|
|
15
|
3569
|
August 29, 2019
|