Upload tokenizer

added_tokens.json

@@ -1,4 +1,6 @@
 {
-  "</s>": 40,
-  "<s>": 39
+  "</s>": 39,
+  "<s>": 38,
+  "[PAD]": 37,
+  "[UNK]": 36
 }

special_tokens_map.json

@@ -1,20 +1,4 @@
 {
-  "additional_special_tokens": [
-    {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false
-    }
-  ],
   "bos_token": "<s>",
   "eos_token": "</s>",
   "pad_token": "[PAD]",

tokenizer_config.json

@@ -1,4 +1,39 @@
 {
+  "added_tokens_decoder": {
+    "36": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "39": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "do_lower_case": false,
@@ -8,6 +43,7 @@
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "tokenizer_file": null,
   "unk_token": "[UNK]",
   "word_delimiter_token": "|"
 }

vocab.json

@@ -1,41 +1,40 @@
 {
-  "+": 1,
-  "[PAD]": 38,
-  "[UNK]": 37,
-  "a": 2,
-  "b": 3,
-  "c": 4,
-  "d": 5,
-  "e": 6,
-  "f": 7,
-  "g": 8,
-  "h": 9,
-  "i": 10,
-  "j": 11,
-  "k": 12,
-  "l": 13,
-  "m": 14,
-  "n": 15,
-  "o": 16,
-  "p": 17,
-  "q": 18,
-  "r": 19,
-  "s": 20,
-  "t": 21,
-  "u": 22,
-  "v": 23,
-  "w": 24,
-  "x": 25,
-  "y": 26,
-  "z": 27,
+  "[PAD]": 37,
+  "[UNK]": 36,
+  "a": 1,
+  "b": 2,
+  "c": 3,
+  "d": 4,
+  "e": 5,
+  "f": 6,
+  "g": 7,
+  "h": 8,
+  "i": 9,
+  "j": 10,
+  "k": 11,
+  "l": 12,
+  "m": 13,
+  "n": 14,
+  "o": 15,
+  "p": 16,
+  "q": 17,
+  "r": 18,
+  "s": 19,
+  "t": 20,
+  "u": 21,
+  "v": 22,
+  "w": 23,
+  "x": 24,
+  "y": 25,
+  "z": 26,
   "|": 0,
-  "á": 28,
-  "ñ": 29,
-  "ī": 30,
-  "ł": 31,
-  "ō": 32,
-  "š": 33,
-  "ū": 34,
-  "ž": 35,
-  "ə": 36
+  "á": 27,
+  "ñ": 28,
+  "ī": 29,
+  "ł": 30,
+  "ō": 31,
+  "š": 32,
+  "ū": 33,
+  "ž": 34,
+  "ə": 35
 }