|
Some Argos Translate updates
|
|
0
|
1924
|
December 11, 2022
|
|
How to speed up beam search?
|
|
5
|
4413
|
March 8, 2017
|
|
How to visualize attention?
|
|
2
|
3497
|
April 16, 2018
|
|
How to estimate number of iterations?
|
|
6
|
4058
|
January 28, 2019
|
|
Is there any way to fine tune Pretrained language models on opennmt?
|
|
6
|
4049
|
December 18, 2019
|
|
Error with Sentencepiece
|
|
6
|
4046
|
July 27, 2021
|
|
Failing conversion of Small100 (SMALL100Tokenizer does not exist or is not currently imported)
|
|
6
|
3998
|
August 1, 2023
|
|
Best way to handle OOV words
|
|
3
|
2970
|
April 30, 2022
|
|
Using OpenNMT with XLM-R Embeddings
|
|
6
|
3987
|
April 9, 2020
|
|
Crash in preprocessing: bad argument #1 to 'ipairs' (table expected, got userdata)
|
|
5
|
4302
|
September 1, 2017
|
|
Looking for a master's thesis topic
|
|
6
|
3974
|
March 4, 2020
|
|
AttributeError: 'list' object has no attribute 'apply'
|
|
4
|
4698
|
June 29, 2020
|
|
CUDA error when using CTranslate2 library compiled on Windows
|
|
3
|
5224
|
December 7, 2021
|
|
WARNING:tensorflow:A checkpoint was restored but not all checkpointed values were used
|
|
1
|
7350
|
December 1, 2020
|
|
English to Chinese
|
|
3
|
2919
|
November 25, 2019
|
|
Multi-gpu PyTorch version?
|
|
5
|
4238
|
June 6, 2017
|
|
CUDA Out-of-memory issue with horovod
|
|
7
|
3657
|
November 30, 2021
|
|
Comparison of online NMT output - English to Indonesian
|
|
0
|
1834
|
March 10, 2018
|
|
Problems in preprocess of Opennmt. Plz help me
|
|
1
|
1294
|
October 2, 2021
|
|
Training loss spikes often, is this normal?
|
|
7
|
3629
|
July 17, 2018
|
|
Server, docker and apache2
|
|
3
|
2885
|
November 19, 2020
|
|
CTranslate2 issues in onmt_server
|
|
4
|
4584
|
November 26, 2020
|
|
Problem with training and validation accuracy
|
|
7
|
3618
|
January 29, 2020
|
|
Token concept in batch_size, training_step, epoch
|
|
3
|
2870
|
April 10, 2022
|
|
State of the art in Machine Translation (2021)
|
|
4
|
4564
|
May 7, 2021
|
|
Maximum_decoding_length explained
|
|
4
|
2565
|
April 8, 2020
|
|
Training loss vs Eval loss
|
|
4
|
4557
|
May 14, 2019
|
|
Character seq2seq - any example / tutorial?
|
|
4
|
4547
|
January 4, 2018
|
|
Where do I get/do you get training data?
|
|
7
|
3576
|
February 21, 2019
|
|
Memory leak in Argos Translate
|
|
5
|
4118
|
February 13, 2024
|
|
Using unigram model with sentencepiece - vocabulary size
|
|
2
|
5774
|
December 19, 2019
|
|
What linguistic features can be added in order to improve translation results?
|
|
5
|
2289
|
February 1, 2024
|
|
Training data for Live System
|
|
6
|
3767
|
March 10, 2017
|
|
Upload, download and edit files through Putty with WinSCP
|
|
3
|
4960
|
July 22, 2018
|
|
Computation of BLEU Score
|
|
5
|
4044
|
February 9, 2020
|
|
Random behaviour in translation wrt punctuation and proper nouns
|
|
7
|
3495
|
July 14, 2019
|
|
Word embedding before training
|
|
5
|
4028
|
March 15, 2017
|
|
RuntimeError: cannot perform reduction function max on tensor with no elements because the operation does not have an identity
|
|
4
|
4403
|
September 10, 2019
|
|
Mini batch size
|
|
3
|
4903
|
May 5, 2017
|
|
Need a proper understanding of the preprocess step
|
|
4
|
4380
|
June 12, 2017
|
|
Questions about word alignment with SentencePiece
|
|
1
|
2173
|
May 8, 2022
|
|
Coming up with a new machine translator based on openNMT
|
|
5
|
3962
|
October 11, 2019
|
|
Two short questions on training
|
|
1
|
1216
|
January 8, 2019
|
|
How perplexity and accuracy being calculated? Where I can I get the explaination?
|
|
2
|
5583
|
September 21, 2017
|
|
Trying to run Inference/Translation server
|
|
6
|
3649
|
October 19, 2021
|
|
[Code Understanding] Decoder in Pytorch
|
|
7
|
3398
|
March 14, 2017
|
|
Question about ctranslate2
|
|
7
|
3392
|
November 1, 2022
|
|
How should I choose parameters?
|
|
0
|
1704
|
February 18, 2017
|
|
English to Tamil and Tamil to English Translation
|
|
4
|
4269
|
January 3, 2018
|
|
Local Attention
|
|
3
|
4766
|
July 8, 2017
|