|
Transformer Error
|
|
1
|
1337
|
October 31, 2019
|
|
Having trouble running toy example
|
|
1
|
1335
|
April 22, 2021
|
|
Bitextor is a tool to automatically harvest bitexts from multilingual websites
|
|
0
|
1885
|
August 30, 2023
|
|
Bpe option in learn_bpe.lua
|
|
1
|
1332
|
October 31, 2017
|
|
Need support for Continuous batching of incoming requests
|
|
1
|
1333
|
September 19, 2023
|
|
Comparing perplexity across different subword segmentations
|
|
0
|
1884
|
May 14, 2020
|
|
Question about meaning of params
|
|
1
|
1331
|
August 3, 2018
|
|
Extracting specific values from inside documents
|
|
3
|
940
|
December 13, 2021
|
|
A w2v-coupled training procedure
|
|
0
|
1880
|
March 12, 2017
|
|
How to use different set of additional features for source and target language
|
|
1
|
1324
|
January 15, 2020
|
|
Does the model see all of the validation set data at each validation step or only the 'valid_batch_size'?
|
|
2
|
1081
|
April 22, 2019
|
|
How to extract the best candidate after token classification?
|
|
3
|
936
|
May 18, 2020
|
|
Asking for an Update to a lower version of Cuda?
|
|
1
|
1323
|
June 3, 2022
|
|
LSTM based seq2seq generate 0, the padding token
|
|
0
|
1871
|
May 31, 2017
|
|
System and reference streams have different lengths
|
|
1
|
1323
|
August 5, 2021
|
|
ZeroDivisionError at ppl
|
|
1
|
1320
|
July 24, 2021
|
|
Unable to use POS tagged dataset for translation
|
|
3
|
933
|
January 22, 2023
|
|
Distributed training on multiple servers
|
|
1
|
1316
|
July 4, 2018
|
|
How to specify the number of layers for Transformer in OpenNMT-tf with Tensorflow 2?
|
|
1
|
1313
|
August 20, 2020
|
|
Forced addition of tokens to the dictionary when used Openmt-tokenizer
|
|
1
|
1312
|
November 19, 2023
|
|
Pre-trained subword embeddings
|
|
3
|
926
|
October 9, 2019
|
|
Problem of attn_debug, dec_attn is {‘std’: None}
|
|
1
|
1308
|
October 13, 2023
|
|
Customized Model for commercial use
|
|
1
|
1308
|
July 15, 2019
|
|
How is google's transformer translate between Chinese and English?
|
|
0
|
1844
|
November 1, 2017
|
|
Is it possible to get attention output of other n_best hypotheses?
|
|
1
|
1300
|
March 28, 2019
|
|
Coding environment for the framework
|
|
1
|
1298
|
May 26, 2017
|
|
Is there any method to force loading the full dataset into memroy instead of lazily load in OpenNMT-py?
|
|
1
|
1298
|
November 25, 2021
|
|
Training success but unable to translate
|
|
1
|
1296
|
March 11, 2019
|
|
Questions regarding visualization
|
|
2
|
1058
|
June 21, 2019
|
|
How to use n_best in python serving?
|
|
1
|
1293
|
December 21, 2021
|
|
Tokenization with POS tagging
|
|
0
|
1824
|
March 14, 2019
|
|
[Outdated] -report_align not working
|
|
3
|
911
|
July 6, 2023
|
|
AttributeError: module 'opennmt.models.catalog' has no attribute 'NMTSmall'
|
|
1
|
1287
|
October 7, 2019
|
|
Saving checkpoint at specified steps
|
|
1
|
1287
|
September 28, 2020
|
|
It can finish training Transformer with 12 layers within 24 hours
|
|
2
|
1047
|
January 6, 2021
|
|
Error in Preprocessing even for the demo code
|
|
2
|
1048
|
January 28, 2020
|
|
Question regarding phrase_table
|
|
2
|
1048
|
September 12, 2019
|
|
Bad alignement line exists. Please check file!
|
|
2
|
1044
|
August 24, 2020
|
|
Two-to-one translation - combined or seperate models?
|
|
1
|
1279
|
April 23, 2025
|
|
About Opennmt-tf 1.25.3 output of exported models
|
|
2
|
1042
|
February 12, 2020
|
|
Translation result becomes a total mess when setting to bigger batch_size
|
|
2
|
1042
|
June 10, 2019
|
|
OpenNMT-py on-the-fly tokenization with subword regularization
|
|
1
|
1279
|
January 26, 2023
|
|
Training on Multi GPU but translating on Single GPU
|
|
1
|
1276
|
April 26, 2018
|
|
Batch size =0 failed (timeout)
|
|
1
|
1273
|
October 22, 2023
|
|
Chinese to english
|
|
1
|
1273
|
February 11, 2019
|
|
Accuracy increases, drops and again increases?
|
|
2
|
1039
|
October 11, 2019
|
|
OpenNMT-py using multiple GPUs results KeyError: 'encoder.embeddings.make_embedding.pe.pe'
|
|
2
|
1037
|
September 20, 2023
|
|
Logger options for rest_translation_server
|
|
1
|
1269
|
July 23, 2017
|
|
Model "jamming" on words
|
|
2
|
1036
|
May 18, 2020
|
|
OpenNMT-py transforms stats
|
|
3
|
897
|
March 30, 2021
|