Larger Vocab = Worse BLEU?
|
|
7
|
300
|
June 25, 2024
|
Using a learned BPE Model for Transformer
|
|
0
|
293
|
March 9, 2024
|
Is there any way I can give custom fairseq config while using fairseq_converter in ctranslate2
|
|
0
|
183
|
February 14, 2024
|
Translation problem using ctranslate2
|
|
13
|
1435
|
February 12, 2024
|
Using SharedEmbeddings Transformer model with Pretrained Embeddings
|
|
0
|
229
|
February 8, 2024
|
Convert ArgosTranslate model to OpenNMT model
|
|
3
|
585
|
February 5, 2024
|
What linguistic features can be added in order to improve translation results?
|
|
5
|
1089
|
February 1, 2024
|
Simple Web Interface
|
|
51
|
6908
|
January 18, 2024
|
Wrong output from exported OpenNMT-tf models
|
|
0
|
315
|
January 15, 2024
|
Training speed with alignment significantly drops down
|
|
0
|
246
|
January 11, 2024
|
Train new SPM model for additional training
|
|
0
|
388
|
December 18, 2023
|
OpenNMT-tf procedure for fine-tuning/domain adaptation?
|
|
6
|
3932
|
May 28, 2019
|
Curriculum Learning in the Age of Transformers - Parts I-II
|
|
8
|
3379
|
July 30, 2023
|
Compile Opennmt-Tf models with AWS neuron sdk
|
|
2
|
499
|
November 26, 2023
|
OpenNMT-tf mixed precision
|
|
0
|
371
|
November 23, 2023
|
Input to reshape is a tensor with 528066 values, but the requested shape has 352022
|
|
0
|
288
|
November 20, 2023
|
Installing OpenNMT-tf on Tesla T4
|
|
4
|
361
|
November 19, 2023
|
Forced addition of tokens to the dictionary when used Openmt-tokenizer
|
|
1
|
381
|
November 19, 2023
|
Is it possible to convert a ctranslate model backward to a marian model?
|
|
2
|
333
|
November 3, 2023
|
Fail to run tflite_test.py
|
|
1
|
336
|
October 26, 2023
|
Batch size =0 failed (timeout)
|
|
1
|
419
|
October 22, 2023
|
cuDNN launch failure After updating tensorflow to 2.13.0
|
|
1
|
448
|
October 2, 2023
|
OpenNMT-tf fine-tune an existing model
|
|
1
|
502
|
September 27, 2023
|
Export saved_model with tflite mode
|
|
0
|
376
|
September 22, 2023
|
H100 perfomance
|
|
0
|
343
|
September 20, 2023
|
How quality of validation dataset affects final results of a model with a fixed number of steps?
|
|
2
|
426
|
September 19, 2023
|
Learning rate start to decay before start_decay_steps
|
|
3
|
371
|
September 8, 2023
|
BLEU decreases so much after averaging checkpoints
|
|
5
|
734
|
March 27, 2022
|
Any negative effects of using the parameter "Replace unknowns = True" in inference?
|
|
3
|
366
|
August 31, 2023
|
OpenNMT-TF checkpoint conversion
|
|
1
|
343
|
August 26, 2023
|