|
The translation results consist entirely of the special character `<unk>`.
|
|
0
|
702
|
August 23, 2024
|
|
How to use pre-trained BPEmb subword embeddings with latest versions of OpenNMT and OpenNMT-py?
|
|
5
|
4249
|
June 16, 2024
|
|
Input to reshape is a tensor with 528066 values, but the requested shape has 352022
|
|
0
|
949
|
November 20, 2023
|
|
Weighted datasets and tokenization
|
|
1
|
944
|
September 19, 2023
|
|
Error converting model to ctranslate2
|
|
5
|
2211
|
April 7, 2023
|
|
Translate_batch(): incompatible function arguments. for ctranslate2
|
|
1
|
3789
|
January 18, 2023
|
|
Low bleu score with Sentencepiece comparing to othoner tokenizers
|
|
2
|
2245
|
August 12, 2022
|
|
Getting no output when usig SentencePiece
|
|
1
|
1427
|
April 23, 2022
|
|
Using Sentencepiece/Byte Pair Encoding on Model
|
|
42
|
23146
|
March 16, 2022
|
|
Overfitting Model
|
|
2
|
1401
|
February 28, 2022
|
|
Question about English to Chinese
|
|
7
|
4303
|
February 17, 2022
|
|
Translation Example in OpenNMT 2.0 Docs
|
|
12
|
4737
|
October 2, 2021
|
|
Single character tokenization?
|
|
10
|
6943
|
August 26, 2021
|
|
Hard spaces lost when tokenizing
|
|
5
|
3042
|
July 19, 2021
|
|
How Much Does Tokenization Affect Neural Machine Translation?
|
|
1
|
2298
|
June 21, 2021
|
|
Different subword tokenization in same word pattern
|
|
3
|
1390
|
November 20, 2020
|
|
Tokenizer v1.20.0 with SentencePiece v0.1.92 potentially problematic?
|
|
5
|
2194
|
October 3, 2020
|
|
Tokenizer (sp_model, vocabulary_threshold) with unexpected results
|
|
6
|
1387
|
September 29, 2020
|
|
How to define the tokenization technique in opennmt-tf
|
|
1
|
1243
|
July 8, 2020
|
|
Korean - English Model
|
|
14
|
5454
|
May 25, 2020
|
|
Tensor conversion/ValueError when training with online tokenizer
|
|
7
|
2372
|
May 11, 2020
|
|
Data not being Tokenized properly
|
|
4
|
1281
|
May 10, 2020
|
|
Character tokenizer with TF2 version
|
|
2
|
1454
|
March 17, 2020
|
|
Problems with pyonmttok
|
|
4
|
3007
|
October 2, 2019
|
|
Core dump while loading the tokenizer
|
|
3
|
1824
|
September 16, 2019
|
|
Issue with special character U+FF5F
|
|
18
|
3103
|
August 14, 2019
|