|
Embeddings training process
|
|
2
|
1680
|
April 12, 2019
|
|
Masking/noise during training
|
|
7
|
1026
|
April 16, 2021
|
|
Slightly different output on localhost vs online
|
|
4
|
1298
|
February 28, 2022
|
|
Question about spliting the sticked words
|
|
7
|
1024
|
May 21, 2019
|
|
From OpenNMT-py To OpenNMT-tf: OOM and other little questions
|
|
2
|
1674
|
July 26, 2019
|
|
Continuing training on a monotext language model
|
|
3
|
1447
|
January 30, 2018
|
|
Word-level Distillation
|
|
1
|
2045
|
December 28, 2017
|
|
How to find that particular word from original text translated to particular word(s)?
|
|
2
|
1668
|
July 7, 2022
|
|
Gradient checking
|
|
2
|
1667
|
August 16, 2017
|
|
Bpe encode with translation_server.lua
|
|
1
|
2041
|
May 30, 2017
|
|
Any recommendation on how to use a trained OpenNMT model on iOS?
|
|
3
|
1441
|
October 25, 2018
|
|
How to control length of output sequence
|
|
1
|
2037
|
December 27, 2016
|
|
Training with the same parameters and date give different results!
|
|
3
|
1439
|
August 3, 2018
|
|
ValueError: Missing field 'vocabulary' in the data configuration in V2.5.0
|
|
6
|
1087
|
January 20, 2020
|
|
Problem regarding serving
|
|
4
|
1285
|
May 28, 2019
|
|
How to use Multi-input in OpenNmt-py?
|
|
1
|
2029
|
May 29, 2018
|
|
How to run TER (translation error rate)
|
|
2
|
1653
|
November 19, 2020
|
|
Convert OpenNMT-TF model to CTranslate2
|
|
4
|
1279
|
July 7, 2021
|
|
External reward signal for human-in-the-loop training
|
|
2
|
1650
|
January 20, 2017
|
|
CUDA Out of memory with sentencepiece
|
|
2
|
1649
|
November 27, 2020
|
|
Efficient implementation for training with uneven batch
|
|
2
|
1643
|
April 7, 2017
|
|
Weights initialization seems not random
|
|
2
|
1640
|
February 2, 2018
|
|
UnicodeEncodeError for build vocab
|
|
4
|
1271
|
November 25, 2020
|
|
Error after evaluation with FP16
|
|
3
|
1416
|
February 11, 2019
|
|
Word Segmentation of Myanmar Language
|
|
1
|
2000
|
June 6, 2018
|
|
ValueError: Cannot use sin/cos positional encoding with odd dim (got dim=515)
|
|
4
|
1264
|
July 15, 2020
|
|
How do I use ConvS2S, RNNattention in OpenNMT-py?
|
|
4
|
1263
|
July 18, 2019
|
|
No Language Left Unlocked dataset
|
|
1
|
1995
|
September 4, 2023
|
|
"unknown" words with BPE tokenization
|
|
1
|
1994
|
February 20, 2017
|
|
Same source/target embeddings for intralingual task
|
|
2
|
1624
|
February 9, 2017
|
|
Summarization / NLP
|
|
2
|
1623
|
November 11, 2019
|
|
Scorer - Test set vs Validation set
|
|
3
|
1406
|
July 2, 2021
|
|
Version 2.2 Perl MultiBleu Script
|
|
3
|
1402
|
July 2, 2021
|
|
Why the gpu use ratio is low?
|
|
3
|
1402
|
May 3, 2019
|
|
Why is it hard for bidirectional to learn to output input
|
|
3
|
1399
|
August 10, 2018
|
|
OpenNMT-py 3 Better Transformer
|
|
2
|
1613
|
November 24, 2022
|
|
How to use multi-gpu while training
|
|
1
|
1975
|
July 31, 2018
|
|
Alternate method of requesting vocab_size during preprocessing
|
|
2
|
1612
|
March 2, 2017
|
|
CUDA out of memory error
|
|
6
|
1058
|
May 12, 2022
|
|
Transformer drops long sentences when translating
|
|
1
|
1973
|
May 27, 2021
|
|
Onmt_train error : The following commands are required: -data/--data
|
|
1
|
1973
|
November 23, 2020
|
|
Extra token produced
|
|
6
|
1054
|
July 26, 2023
|
|
How to make Serving for Multi-Feature Transformer Model?
|
|
3
|
1394
|
January 10, 2020
|
|
Why NLL loss is not normalized by the number of tokens?
|
|
1
|
1972
|
September 22, 2019
|
|
Unicode normalization type
|
|
2
|
1607
|
October 12, 2022
|
|
Vocabulary size with src_vocab and tgt_vocab
|
|
2
|
1605
|
May 20, 2019
|
|
Handling single word 1 to many translation
|
|
2
|
1606
|
November 6, 2021
|
|
Faster Whisper runtimeError: Unsupported model binary version.
|
|
0
|
2782
|
September 11, 2024
|
|
Where can I find sota BLEU scores results for various language pairs?
|
|
2
|
1602
|
April 11, 2019
|
|
Extract / Dissect / Freeze Transformer's Encoder Decoder Components
|
|
3
|
1388
|
June 7, 2024
|