Topics tagged tokenizer

Topic	Replies	Views	Activity
The translation results consist entirely of the special character `<unk>`. Community tokenizer , opennmt-py	0	189	August 23, 2024
How to use pre-trained BPEmb subword embeddings with latest versions of OpenNMT and OpenNMT-py? Support opennmt-py , tokenizer	5	2356	June 16, 2024
Input to reshape is a tensor with 528066 values, but the requested shape has 352022 Support tokenizer , opennmt-tf	0	374	November 20, 2023
Weighted datasets and tokenization Feature Requests tokenizer	1	482	September 19, 2023
Error converting model to ctranslate2 Support tokenizer , ctranslate2 , opennmt-tf	5	1256	April 7, 2023
Translate_batch(): incompatible function arguments. for ctranslate2 Support ctranslate2 , tokenizer , opennmt-tf	1	1705	January 18, 2023
Low bleu score with Sentencepiece comparing to othoner tokenizers Support tokenizer , opennmt-tf	2	1371	August 12, 2022
Getting no output when usig SentencePiece Support opennmt-tf , tokenizer	1	729	April 23, 2022
Using Sentencepiece/Byte Pair Encoding on Model Support opennmt-py , tokenizer	42	14062	March 16, 2022
Overfitting Model Support opennmt-py , tokenizer	2	958	February 28, 2022
Question about English to Chinese Support tokenizer , opennmt-tf	7	2461	February 17, 2022
Translation Example in OpenNMT 2.0 Docs Tutorials tokenizer , opennmt-py	12	2558	October 2, 2021
Single character tokenization? Research tokenizer	10	5030	August 26, 2021
Hard spaces lost when tokenizing Support tokenizer	5	1727	July 19, 2021
How Much Does Tokenization Affect Neural Machine Translation? Research tokenizer	1	1560	June 21, 2021
Different subword tokenization in same word pattern Support opennmt-tf , tokenizer	3	818	November 20, 2020
Tokenizer v1.20.0 with SentencePiece v0.1.92 potentially problematic? Development tokenizer	5	1286	October 3, 2020
Tokenizer (sp_model, vocabulary_threshold) with unexpected results Support tokenizer	6	901	September 29, 2020
How to define the tokenization technique in opennmt-tf Support tokenizer , opennmt-tf	1	862	July 8, 2020
Korean - English Model Support tokenizer	14	4081	May 25, 2020
Tensor conversion/ValueError when training with online tokenizer Support tokenizer , opennmt-tf	7	1575	May 11, 2020
Data not being Tokenized properly Support opennmt-tf , tokenizer	4	856	May 10, 2020
Character tokenizer with TF2 version Support tokenizer , opennmt-tf	2	1031	March 17, 2020
Problems with pyonmttok Support opennmt-py , tokenizer	4	1984	October 2, 2019
Core dump while loading the tokenizer Support tokenizer , opennmt-py	3	1397	September 16, 2019
Issue with special character U+FF5F Support opennmt-tf , tokenizer	18	2326	August 14, 2019