Upload tokenizer

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
-base_model: facebook/hubert-large-ll60k
 tags:
 - generated_from_trainer
+base_model: facebook/hubert-large-ll60k
 metrics:
 - wer
 model-index:

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 37,
-  "<s>": 36
+  "</s>": 119,
+  "<s>": 118
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "34": {
+    "116": {
       "content": "[UNK]",
       "lstrip": false,
       "normalized": true,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": true
     },
-    "35": {
+    "117": {
       "content": "[PAD]",
       "lstrip": false,
       "normalized": true,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "36": {
+    "118": {
       "content": "<s>",
       "lstrip": false,
       "normalized": true,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "37": {
+    "119": {
       "content": "</s>",
       "lstrip": false,
       "normalized": true,

vocab.json

@@ -1,38 +1,120 @@
 {
   " ": 0,
-  "!": 1,
-  "\"": 2,
-  "'": 3,
-  ",": 4,
-  ".": 5,
-  ":": 6,
-  "?": 7,
-  "A": 8,
-  "B": 9,
-  "C": 10,
-  "D": 11,
-  "E": 12,
-  "F": 13,
-  "G": 14,
-  "H": 15,
-  "I": 16,
-  "J": 17,
-  "K": 18,
-  "L": 19,
-  "M": 20,
-  "N": 21,
-  "O": 22,
-  "P": 23,
-  "Q": 24,
-  "R": 25,
-  "S": 26,
-  "T": 27,
-  "U": 28,
-  "V": 29,
-  "W": 30,
-  "X": 31,
-  "Y": 32,
-  "Z": 33,
-  "[PAD]": 35,
-  "[UNK]": 34
+  "<DEL>": 1,
+  "<unk>": 2,
+  "AA": 3,
+  "AA0": 4,
+  "AA1": 5,
+  "AA2": 6,
+  "AE": 7,
+  "AE*": 8,
+  "AE0": 9,
+  "AE1": 10,
+  "AE2": 11,
+  "AH": 12,
+  "AH*": 13,
+  "AH0": 14,
+  "AH1": 15,
+  "AH2": 16,
+  "AO": 17,
+  "AO*": 18,
+  "AO0": 19,
+  "AO1": 20,
+  "AO2": 21,
+  "AR": 22,
+  "AW": 23,
+  "AW0": 24,
+  "AW1": 25,
+  "AW2": 26,
+  "AY": 27,
+  "AY*": 28,
+  "AY0": 29,
+  "AY1": 30,
+  "AY2": 31,
+  "B": 32,
+  "B*": 33,
+  "CH": 34,
+  "CH*": 35,
+  "D": 36,
+  "D*": 37,
+  "DH": 38,
+  "DR": 39,
+  "DZ": 40,
+  "EH": 41,
+  "EH*": 42,
+  "EH0": 43,
+  "EH1": 44,
+  "EH2": 45,
+  "ER": 46,
+  "ER*": 47,
+  "ER0": 48,
+  "ER1": 49,
+  "EY": 50,
+  "EY*": 51,
+  "EY0": 52,
+  "EY1": 53,
+  "EY2": 54,
+  "F": 55,
+  "F*": 56,
+  "G": 57,
+  "G*": 58,
+  "HH": 59,
+  "IH": 60,
+  "IH*": 61,
+  "IH0": 62,
+  "IH1": 63,
+  "IH2": 64,
+  "IR": 65,
+  "IY": 66,
+  "IY*": 67,
+  "IY0": 68,
+  "IY1": 69,
+  "JH": 70,
+  "JH*": 71,
+  "K": 72,
+  "K*": 73,
+  "L": 74,
+  "L*": 75,
+  "M": 76,
+  "M*": 77,
+  "N": 78,
+  "N*": 79,
+  "NG": 80,
+  "NG*": 81,
+  "OW": 82,
+  "OW*": 83,
+  "OW0": 84,
+  "OW1": 85,
+  "OY0": 86,
+  "OY1": 87,
+  "P": 88,
+  "P*": 89,
+  "R": 90,
+  "R*": 91,
+  "S": 92,
+  "S*": 93,
+  "SH": 94,
+  "T": 95,
+  "T*": 96,
+  "TH": 97,
+  "TH*": 98,
+  "TR": 99,
+  "TS": 100,
+  "UH": 101,
+  "UH*": 102,
+  "UH0": 103,
+  "UH1": 104,
+  "UW": 105,
+  "UW0": 106,
+  "UW1": 107,
+  "UW2": 108,
+  "V": 109,
+  "V*": 110,
+  "W": 111,
+  "W*": 112,
+  "Y": 113,
+  "Z": 114,
+  "ZH": 115,
+  "[PAD]": 117,
+  "[UNK]": 116
 }