Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 35,
-  "<s>": 34
+  "</s>": 42,
+  "<s>": 41
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "32": {
+    "39": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "33": {
+    "40": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "34": {
+    "41": {
       "content": "<s>",
       "lstrip": false,
       "normalized": true,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "35": {
+    "42": {
       "content": "</s>",
       "lstrip": false,
       "normalized": true,

vocab.json

@@ -1,36 +1,43 @@
 {
-  "[PAD]": 33,
-  "[UNK]": 32,
-  "\\": 1,
-  "_": 2,
-  "a": 3,
-  "b": 4,
-  "c": 5,
-  "d": 6,
-  "e": 7,
-  "f": 8,
-  "g": 9,
-  "h": 10,
-  "i": 11,
-  "j": 12,
-  "k": 13,
-  "l": 14,
-  "m": 15,
-  "n": 16,
-  "o": 17,
-  "p": 18,
-  "q": 19,
-  "r": 20,
-  "s": 21,
-  "t": 22,
-  "u": 23,
-  "v": 24,
-  "w": 25,
-  "x": 26,
-  "y": 27,
-  "z": 28,
+  "[PAD]": 40,
+  "[UNK]": 39,
+  "a": 1,
+  "b": 2,
+  "d": 3,
+  "e": 4,
+  "f": 5,
+  "h": 6,
+  "i": 7,
+  "j": 8,
+  "k": 9,
+  "l": 10,
+  "m": 11,
+  "n": 12,
+  "o": 13,
+  "p": 14,
+  "r": 15,
+  "s": 16,
+  "t": 17,
+  "u": 18,
+  "v": 19,
+  "w": 20,
+  "x": 21,
+  "y": 22,
+  "z": 23,
   "|": 0,
-  "£": 29,
-  "æ": 30,
-  "ø": 31
+  "ø": 24,
+  "ŋ": 25,
+  "œ": 26,
+  "ɑ": 27,
+  "ɔ": 28,
+  "ə": 29,
+  "ɛ": 30,
+  "ɡ": 31,
+  "ɪ": 32,
+  "ɹ": 33,
+  "ʂ": 34,
+  "ʃ": 35,
+  "ʉ": 36,
+  "ʊ": 37,
+  "ː": 38
 }