aboutsummaryrefslogtreecommitdiff
path: root/data/tokenizers/char_tokenizer_german.json
diff options
context:
space:
mode:
authorPherkel2023-09-12 14:19:15 +0200
committerGitHub2023-09-12 14:19:15 +0200
commit7a9a6c783e69b5a537a3d3f5bfe8d5fdc656c807 (patch)
tree0725631b9b68aeb65b292420a15941dcfa3fc04f /data/tokenizers/char_tokenizer_german.json
parentf9846193289c81d89342b6a36e951605c2cfa189 (diff)
parent7b71dab87591e04d874cd636614450b0e65e3f2b (diff)
Merge pull request #37 from Algo-Boys/fix/ultimate
Fix/ultimate
Diffstat (limited to 'data/tokenizers/char_tokenizer_german.json')
-rw-r--r--data/tokenizers/char_tokenizer_german.json38
1 files changed, 38 insertions, 0 deletions
diff --git a/data/tokenizers/char_tokenizer_german.json b/data/tokenizers/char_tokenizer_german.json
new file mode 100644
index 0000000..20db079
--- /dev/null
+++ b/data/tokenizers/char_tokenizer_german.json
@@ -0,0 +1,38 @@
+_ 0
+<BLANK> 1
+<UNK> 2
+<SPACE> 3
+a 4
+b 5
+c 6
+d 7
+e 8
+f 9
+g 10
+h 11
+i 12
+j 13
+k 14
+l 15
+m 16
+n 17
+o 18
+p 19
+q 20
+r 21
+s 22
+t 23
+u 24
+v 25
+w 26
+x 27
+y 28
+z 29
+é 30
+à 31
+ä 32
+ö 33
+ß 34
+ü 35
+- 36
+' 37