summaryrefslogtreecommitdiff
path: root/training/conf/mapping
diff options
context:
space:
mode:
authorGustaf Rydholm <gustaf.rydholm@gmail.com>2021-07-29 23:59:52 +0200
committerGustaf Rydholm <gustaf.rydholm@gmail.com>2021-07-29 23:59:52 +0200
commit34098ccbbbf6379c0bd29a987440b8479c743746 (patch)
treea8c68e3036503049fc7034c677ec855465f7a8e0 /training/conf/mapping
parentc032ffb05a7ed86f8fe5d596f94e8997c558cae8 (diff)
Configs, refactor with attrs, fix attr bug in iam
Diffstat (limited to 'training/conf/mapping')
-rw-r--r--training/conf/mapping/word_piece.yaml9
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"]