|
CTranslate2 on OpenNMT-py Server
|
|
13
|
5842
|
February 1, 2021
|
|
SDL Trados Studio integration
|
|
21
|
8255
|
September 8, 2017
|
|
RuntimeError: value cannot be converted to type float without overflow
|
|
12
|
10488
|
July 30, 2019
|
|
Translation server crashing after initialization
|
|
31
|
6100
|
March 7, 2017
|
|
Best way to handle emojis during translation
|
|
37
|
5562
|
June 3, 2020
|
|
Validation Data
|
|
15
|
8387
|
March 14, 2017
|
|
Convert M2M model to CTranslate2
|
|
12
|
9130
|
June 20, 2022
|
|
Pre-processing corpora
|
|
23
|
6581
|
December 12, 2017
|
|
OpenNMT-py BERT Tutorial
|
|
13
|
8502
|
October 13, 2021
|
|
First OpenNMT Workshop in Paris - Registration is open!
|
|
13
|
4773
|
March 1, 2018
|
|
Load a savedmodel in tensorFlow
|
|
18
|
7261
|
April 12, 2022
|
|
OpenNMT-py error when training with large amount of data
|
|
21
|
6609
|
November 6, 2022
|
|
Are you interested in training Russian-Abkhazian parallel corpus?
|
|
29
|
5644
|
June 9, 2020
|
|
Epochs Determination
|
|
21
|
6376
|
April 2, 2024
|
|
Multi-GPUs is slower than single GPU
|
|
12
|
8288
|
April 16, 2019
|
|
Issues when running the English-German WMT15 training
|
|
22
|
6110
|
November 22, 2018
|
|
Bpe, vocab size
|
|
20
|
6308
|
August 3, 2021
|
|
Tokenize.lua results in
|
|
16
|
7007
|
June 23, 2017
|
|
Linguistic features surprisingly decrease the performance!
|
|
19
|
6392
|
May 14, 2019
|
|
Sentence length & translation quality
|
|
13
|
7458
|
June 11, 2018
|
|
Improvement of performance by data normalization
|
|
23
|
5670
|
August 16, 2019
|
|
Ensemble decoding
|
|
16
|
6520
|
October 19, 2017
|
|
Ctranslate2 client did not work in windows
|
|
15
|
6712
|
July 14, 2021
|
|
How to resume training from last interupted state
|
|
11
|
4338
|
July 21, 2019
|
|
In-domain training
|
|
14
|
3835
|
March 19, 2017
|
|
Fine tuning nllb-200-distilled-600M model
|
|
16
|
6136
|
April 15, 2024
|
|
Leave Unknown Words Untranslated
|
|
17
|
5892
|
December 19, 2019
|
|
Bleu score falling when detokenizing, detruecasing and de subword BPE
|
|
16
|
5971
|
March 23, 2023
|
|
Pretrained Model English<->German
|
|
13
|
3637
|
February 14, 2017
|
|
Supporting Tokenize/Detokenize automatically by Translation Server
|
|
17
|
5696
|
September 11, 2017
|
|
Install ctranslate2 wheel from gpu docker image
|
|
12
|
6665
|
January 15, 2021
|
|
Issue in using distributed training in openNMT-TF
|
|
31
|
4220
|
November 21, 2018
|
|
Terminology handling
|
|
16
|
5720
|
September 8, 2023
|
|
Single character tokenization?
|
|
10
|
7097
|
August 26, 2021
|
|
Some experience when training with large datasets
|
|
17
|
5534
|
November 1, 2017
|
|
Size of feature embeddings (and some digression about casing methods)
|
|
17
|
5506
|
July 29, 2020
|
|
Where can I find sentencepiece_model of my model?
|
|
12
|
6283
|
January 29, 2020
|
|
Training Won't resume from latest checkpoint
|
|
14
|
5806
|
September 4, 2022
|
|
Korean - English Model
|
|
14
|
5621
|
May 25, 2020
|
|
Installed but can't get pre-processing working
|
|
16
|
5224
|
November 25, 2019
|
|
TensorFlow REST API + SentencePiece
|
|
19
|
4647
|
August 30, 2021
|
|
Convert to Keras Model for CoreMlTools
|
|
16
|
4980
|
June 4, 2021
|
|
Preprocessing corpus for case_feature and POS tags
|
|
12
|
5641
|
March 22, 2018
|
|
XML tags handling
|
|
18
|
4638
|
October 23, 2018
|
|
Teacher forcing
|
|
11
|
5633
|
July 25, 2017
|
|
End and Start Tokens
|
|
11
|
5574
|
November 29, 2021
|
|
DataLossError : Checksum does not match
|
|
10
|
5768
|
May 18, 2019
|
|
Detokenization clarification
|
|
10
|
5551
|
January 11, 2017
|
|
RuntimeError: Model diverged with loss = NaN
|
|
13
|
4890
|
February 21, 2020
|
|
Using EmbeddingsSharingLevel in a dual source transformer
|
|
22
|
3806
|
June 19, 2020
|