Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 72,
+  "<s>": 71
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "added_tokens_decoder": {
+    "69": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "72": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": "eng",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,75 @@
+{
+  "eng": {
+    "%": 1,
+    "'": 2,
+    ",": 3,
+    "-": 4,
+    ".": 5,
+    "0": 6,
+    "1": 7,
+    "2": 8,
+    "3": 9,
+    "4": 10,
+    "5": 11,
+    "6": 12,
+    "7": 13,
+    "8": 14,
+    "9": 15,
+    "?": 16,
+    "A": 17,
+    "B": 18,
+    "C": 19,
+    "D": 20,
+    "E": 21,
+    "F": 22,
+    "G": 23,
+    "H": 24,
+    "I": 25,
+    "J": 26,
+    "K": 27,
+    "L": 28,
+    "M": 29,
+    "N": 30,
+    "O": 31,
+    "P": 32,
+    "Q": 33,
+    "R": 34,
+    "S": 35,
+    "T": 36,
+    "U": 37,
+    "V": 38,
+    "W": 39,
+    "X": 40,
+    "Y": 41,
+    "Z": 42,
+    "[PAD]": 70,
+    "[UNK]": 69,
+    "a": 43,
+    "b": 44,
+    "c": 45,
+    "d": 46,
+    "e": 47,
+    "f": 48,
+    "g": 49,
+    "h": 50,
+    "i": 51,
+    "j": 52,
+    "k": 53,
+    "l": 54,
+    "m": 55,
+    "n": 56,
+    "o": 57,
+    "p": 58,
+    "q": 59,
+    "r": 60,
+    "s": 61,
+    "t": 62,
+    "u": 63,
+    "v": 64,
+    "w": 65,
+    "x": 66,
+    "y": 67,
+    "z": 68,
+    "|": 0
+  }
+}