|
The model is outputting <UNKs>
|
|
5
|
2830
|
January 1, 2021
|
|
Erro raised while using openNMT-tf to train a chinese->english engine
|
|
8
|
2310
|
April 3, 2018
|
|
Using OpenNMT for Information Retrieval
|
|
3
|
1940
|
May 27, 2018
|
|
Python Tool for language translation using OpenNMT
|
|
8
|
2297
|
February 26, 2019
|
|
Shuffle samples during training
|
|
7
|
2439
|
March 16, 2020
|
|
Change opus format to be similar to toy dataset
|
|
0
|
1225
|
November 1, 2022
|
|
GitHub - dothq/translate: 🌐 Translation microservice powered by OpenNMT
|
|
0
|
1221
|
November 30, 2021
|
|
How to use copy-mechanism in OpenNMT-tf?
|
|
6
|
2597
|
March 28, 2018
|
|
Re-training Existing Model with Monolingual Corpora
|
|
7
|
2427
|
August 29, 2018
|
|
Under what conditions should CTranslate2 GPU translation be faster than CPU
|
|
1
|
4851
|
November 18, 2022
|
|
Error whey saving vocab file in openmt-py
|
|
1
|
1528
|
January 25, 2021
|
|
How to check if onmt-main is using my GPU
|
|
4
|
3056
|
October 16, 2018
|
|
MS Azure image?
|
|
1
|
1523
|
March 9, 2017
|
|
Getting encoder embeddings for words from the model
|
|
4
|
1707
|
November 30, 2023
|
|
The difference between parameter
|
|
8
|
2261
|
January 4, 2017
|
|
Multi function REST API
|
|
5
|
2769
|
October 20, 2018
|
|
Words are lost when transforme long sentences
|
|
5
|
2763
|
October 22, 2020
|
|
Model with bidirectional translation
|
|
3
|
3375
|
July 26, 2017
|
|
Does continuing training start from unseen/less-seen data?
|
|
5
|
2745
|
February 22, 2021
|
|
Linker error when compiling CTranslate2 with "-march=corei7-avx" (CXX_FLAGS)
|
|
6
|
2533
|
September 12, 2020
|
|
No <unk> token in the dataset but <unk> is generated in the end of all output sentences
|
|
3
|
3347
|
April 12, 2018
|
|
Wrong word UNK replacement
|
|
7
|
2371
|
October 15, 2019
|
|
ImportError: No module named torchtext.data
|
|
1
|
4719
|
May 1, 2018
|
|
About Confident score
|
|
8
|
2223
|
July 4, 2021
|
|
Multimodal feature input for seq2seq
|
|
7
|
2358
|
August 11, 2021
|
|
-fix_word_vecs_enc and -fix_word_vecs_dec not doing what I expect them to do
|
|
7
|
2355
|
September 16, 2019
|
|
Tokenizer v1.20.0 with SentencePiece v0.1.92 potentially problematic?
|
|
5
|
2718
|
October 3, 2020
|
|
Get VMap from the corpus to be used in CTranslate2
|
|
8
|
2219
|
March 24, 2020
|
|
Large perplexity
|
|
6
|
2514
|
December 12, 2018
|
|
Is it normal to see "Weighted corpora loaded so far" in a loop during the finetuning phase on a very small dataset?
|
|
6
|
2508
|
February 15, 2024
|
|
AI Grant announcement
|
|
1
|
2636
|
July 27, 2017
|
|
Automatic post-edit training of a training
|
|
5
|
2710
|
June 14, 2018
|
|
ONMT net structure?
|
|
5
|
2707
|
May 11, 2018
|
|
Abnormal perplexity results on Chinese dialogue dataset using transformer
|
|
0
|
1178
|
January 3, 2021
|
|
Tracking Training progress
|
|
1
|
1476
|
December 20, 2021
|
|
Could I submit pull request to tokenization hook for Korean and Japanese?
|
|
3
|
1853
|
May 23, 2018
|
|
Assert model_dim % head_count == 0
|
|
1
|
1473
|
November 8, 2022
|
|
OpenNMT translate string as an input
|
|
4
|
2946
|
October 12, 2018
|
|
SentencePiece + pyonmttok
|
|
5
|
2679
|
July 4, 2021
|
|
Exposure bias during training
|
|
3
|
3279
|
August 10, 2017
|
|
IndexError: list index out of range error
|
|
2
|
3786
|
November 7, 2019
|
|
OpenNMT-tf Fine tuning base model gives worse and decreases BLEU scores
|
|
8
|
2188
|
December 5, 2018
|
|
Using a pretrained summarization model on a new document
|
|
3
|
3262
|
March 11, 2017
|
|
"-add_tokenized_output "option in rest_translation_server.lua
|
|
8
|
2174
|
May 10, 2018
|
|
AttributeError: 'SequenceRecordInputter' object has no attribute 'input_depth'
|
|
5
|
2653
|
March 22, 2019
|
|
Training crash at validation
|
|
4
|
2904
|
July 1, 2021
|
|
Errors when trying to load model exported by OpenNMT-tf
|
|
2
|
3749
|
February 28, 2019
|
|
Inferencing with translate.py
|
|
6
|
2456
|
March 9, 2022
|
|
Bi-directional language model
|
|
3
|
3242
|
April 10, 2018
|
|
Reproducing pre-trained Transformer model
|
|
8
|
2156
|
April 16, 2020
|