Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 97,
-  "<s>": 96
+  "</s>": 50,
+  "<s>": 49
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "94": {
+    "47": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "95": {
+    "48": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "96": {
+    "49": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "97": {
+    "50": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -39,7 +39,6 @@
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
-  "processor_class": "Wav2Vec2BertProcessor",
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

vocab.json

@@ -1,98 +1,51 @@
 {
-  "!": 1,
-  "\"": 2,
-  "&": 3,
-  "'": 4,
-  ",": 5,
-  "-": 6,
-  ".": 7,
-  ":": 8,
-  ";": 9,
-  "?": 10,
-  "A": 11,
-  "B": 12,
-  "C": 13,
-  "D": 14,
-  "E": 15,
-  "F": 16,
-  "G": 17,
-  "H": 18,
-  "I": 19,
-  "J": 20,
-  "K": 21,
-  "L": 22,
-  "M": 23,
-  "N": 24,
-  "O": 25,
-  "P": 26,
-  "Q": 27,
-  "R": 28,
-  "S": 29,
-  "T": 30,
-  "U": 31,
-  "V": 32,
-  "W": 33,
-  "X": 34,
-  "Y": 35,
-  "Z": 36,
-  "[PAD]": 95,
-  "[UNK]": 94,
-  "a": 37,
-  "b": 38,
-  "c": 39,
-  "d": 40,
-  "e": 41,
-  "f": 42,
-  "g": 43,
-  "h": 44,
-  "i": 45,
-  "j": 46,
-  "k": 47,
-  "l": 48,
-  "m": 49,
-  "n": 50,
-  "o": 51,
-  "p": 52,
-  "q": 53,
-  "r": 54,
-  "s": 55,
-  "t": 56,
-  "u": 57,
-  "v": 58,
-  "w": 59,
-  "x": 60,
-  "y": 61,
-  "z": 62,
+  "&": 1,
+  "[PAD]": 48,
+  "[UNK]": 47,
+  "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,
   "|": 0,
-  "«": 63,
-  "´": 64,
-  "»": 65,
-  "À": 66,
-  "Á": 67,
-  "Â": 68,
-  "É": 69,
-  "Í": 70,
-  "Ó": 71,
-  "Ô": 72,
-  "Ú": 73,
-  "à": 74,
-  "á": 75,
-  "â": 76,
-  "ã": 77,
-  "ç": 78,
-  "è": 79,
-  "é": 80,
-  "ê": 81,
-  "í": 82,
-  "ñ": 83,
-  "ó": 84,
-  "ô": 85,
-  "õ": 86,
-  "ú": 87,
-  "ü": 88,
-  "š": 89,
-  "ž": 90,
-  "‐": 91,
-  "“": 92,
-  "”": 93
+  "´": 28,
+  "à": 29,
+  "á": 30,
+  "â": 31,
+  "ã": 32,
+  "ç": 33,
+  "è": 34,
+  "é": 35,
+  "ê": 36,
+  "í": 37,
+  "ñ": 38,
+  "ó": 39,
+  "ô": 40,
+  "õ": 41,
+  "ú": 42,
+  "ü": 43,
+  "š": 44,
+  "ž": 45,
+  "‐": 46
 }