|
OpenNMT-py Training takes 4 hours - regardless of corpus size
|
|
2
|
1036
|
April 19, 2019
|
|
Understanding beam search
|
|
2
|
1036
|
October 4, 2018
|
|
Serving with FPGA
|
|
2
|
1034
|
November 23, 2020
|
|
Is there a way to score the validation set against multiple references?
|
|
2
|
1034
|
July 15, 2020
|
|
Exist a way to use the word embedding trained in one model export it and use it as input for another model?
|
|
2
|
1033
|
October 22, 2018
|
|
Any scripts to start multi-nodes training?
|
|
4
|
800
|
September 29, 2022
|
|
How quality of validation dataset affects final results of a model with a fixed number of steps?
|
|
2
|
1032
|
September 19, 2023
|
|
How to know if lua version is using GPU?
|
|
1
|
1264
|
June 25, 2018
|
|
Ctranslate2 - TypeError: 'str' object is collable
|
|
2
|
1031
|
October 28, 2020
|
|
Channels error while translating
|
|
1
|
1262
|
November 11, 2019
|
|
Preprocess.lua Empty Dataset Error
|
|
2
|
1028
|
November 2, 2018
|
|
<unk> tokens in every inference from optimized model
|
|
1
|
1259
|
April 1, 2020
|
|
Consulting support to validate a solution
|
|
1
|
1259
|
June 14, 2019
|
|
LSTM based seq2seq generate 0, the padding token
|
|
0
|
1773
|
May 31, 2017
|
|
How to Pass Nested Config Values to Runner
|
|
2
|
1023
|
May 6, 2020
|
|
Nbest feature during translation with pytorch
|
|
4
|
792
|
February 13, 2020
|
|
Training doesn't start with start_from for domain training
|
|
2
|
1021
|
March 25, 2019
|
|
About summarization ROUGE score
|
|
0
|
1767
|
June 11, 2021
|
|
Conversion of factored Marian models to CTranslate2
|
|
2
|
1019
|
November 4, 2024
|
|
Running two models at the same run
|
|
3
|
884
|
December 3, 2020
|
|
How is google's transformer translate between Chinese and English?
|
|
0
|
1765
|
November 1, 2017
|
|
How should I adjust the parameters
|
|
2
|
1018
|
October 26, 2022
|
|
Not able to convert the hidden states to tensor post infer from the ctranslate model
|
|
0
|
1765
|
August 25, 2025
|
|
Decoding with LM
|
|
1
|
1245
|
April 28, 2019
|
|
Translating to new languages
|
|
2
|
1015
|
September 30, 2019
|
|
Doubt with Number of Epoch
|
|
1
|
1243
|
May 11, 2020
|
|
Having trouble running toy example
|
|
1
|
1242
|
April 22, 2021
|
|
"keep_checkpoint_max" in eval parameters group?
|
|
1
|
1242
|
April 4, 2020
|
|
Retrieving all Hypotheses in the Python Client
|
|
3
|
877
|
December 18, 2019
|
|
Error in training using embeddings
|
|
1
|
1238
|
August 28, 2019
|
|
How use multi-feature model for domain adaptation
|
|
3
|
874
|
April 28, 2020
|
|
How to restrict the output sequence length
|
|
1
|
1236
|
January 2, 2020
|
|
cuDNN launch failure After updating tensorflow to 2.13.0
|
|
1
|
1233
|
October 2, 2023
|
|
Comparing perplexity across different subword segmentations
|
|
0
|
1741
|
May 14, 2020
|
|
Recommendations for breaking down input text for inference
|
|
2
|
1004
|
August 31, 2020
|
|
Opennmt-tf not recognizing GPU
|
|
3
|
868
|
April 4, 2022
|
|
A w2v-coupled training procedure
|
|
0
|
1730
|
March 12, 2017
|
|
How can use -start_epoch in OpenNMT-py?
|
|
2
|
998
|
September 15, 2018
|
|
Tqdm with translate_batch()
|
|
1
|
1222
|
December 8, 2021
|
|
Transformer Error
|
|
1
|
1222
|
October 31, 2019
|
|
How to use different set of additional features for source and target language
|
|
1
|
1223
|
January 15, 2020
|
|
Question about meaning of params
|
|
1
|
1222
|
August 3, 2018
|
|
Speech to text decoding of text
|
|
2
|
994
|
November 22, 2019
|
|
ZeroDivisionError at ppl
|
|
1
|
1218
|
July 24, 2021
|
|
OpenNMT-tf fine-tune an existing model
|
|
1
|
1216
|
September 27, 2023
|
|
Distributed training on multiple servers
|
|
1
|
1216
|
July 4, 2018
|
|
Empty lines returned by model
|
|
3
|
859
|
September 14, 2020
|
|
System and reference streams have different lengths
|
|
1
|
1213
|
August 5, 2021
|
|
Customized Model for commercial use
|
|
1
|
1213
|
July 15, 2019
|
|
Is there a way to connect my model to Memsource
|
|
2
|
989
|
February 9, 2021
|