diff options
Diffstat (limited to 'training/conf/mapping')
| -rw-r--r-- | training/conf/mapping/word_piece.yaml | 9 |
1 files changed, 9 insertions, 0 deletions
diff --git a/training/conf/mapping/word_piece.yaml b/training/conf/mapping/word_piece.yaml new file mode 100644 index 0000000..39e2ba4 --- /dev/null +++ b/training/conf/mapping/word_piece.yaml @@ -0,0 +1,9 @@ +_target_: text_recognizer.data.mappings.WordPieceMapping +num_features: 1000 +tokens: iamdb_1kwp_tokens_1000.txt +lexicon: iamdb_1kwp_lex_1000.txt +data_dir: null +use_words: false +prepend_wordsep: false +special_tokens: ["<s>", "<e>", "<p>"] +extra_symbols: ["\n"] |