Upload tokenizer

README.md

@@ -1,10 +1,10 @@
 ---
-license: apache-2.0
 base_model: facebook/wav2vec2-xls-r-300m
-tags:
-- generated_from_trainer
+license: apache-2.0
 metrics:
 - wer
+tags:
+- generated_from_trainer
 model-index:
 - name: wav2vec2-large-xls-r-300m-hindi_marathi-colab
   results: []

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 155,
+  "<s>": 154
+}

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 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "152": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "155": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "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]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,156 @@
+{
+  " ": 0,
+  "!": 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,
+  "R": 27,
+  "S": 28,
+  "T": 29,
+  "V": 30,
+  "W": 31,
+  "X": 32,
+  "Y": 33,
+  "Z": 34,
+  "[PAD]": 153,
+  "[UNK]": 152,
+  "a": 35,
+  "b": 36,
+  "c": 37,
+  "d": 38,
+  "e": 39,
+  "f": 40,
+  "g": 41,
+  "h": 42,
+  "i": 43,
+  "j": 44,
+  "k": 45,
+  "l": 46,
+  "m": 47,
+  "n": 48,
+  "o": 49,
+  "p": 50,
+  "q": 51,
+  "r": 52,
+  "s": 53,
+  "t": 54,
+  "u": 55,
+  "v": 56,
+  "w": 57,
+  "x": 58,
+  "y": 59,
+  "z": 60,
+  "|": 61,
+  "ँ": 62,
+  "ं": 63,
+  "ः": 64,
+  "अ": 65,
+  "आ": 66,
+  "इ": 67,
+  "ई": 68,
+  "उ": 69,
+  "ऊ": 70,
+  "ऋ": 71,
+  "ऌ": 72,
+  "ऍ": 73,
+  "ऎ": 74,
+  "ए": 75,
+  "ऐ": 76,
+  "ऑ": 77,
+  "ओ": 78,
+  "औ": 79,
+  "क": 80,
+  "ख": 81,
+  "ग": 82,
+  "घ": 83,
+  "ङ": 84,
+  "च": 85,
+  "छ": 86,
+  "ज": 87,
+  "झ": 88,
+  "ञ": 89,
+  "ट": 90,
+  "ठ": 91,
+  "ड": 92,
+  "ढ": 93,
+  "ण": 94,
+  "त": 95,
+  "थ": 96,
+  "द": 97,
+  "ध": 98,
+  "न": 99,
+  "प": 100,
+  "फ": 101,
+  "ब": 102,
+  "भ": 103,
+  "म": 104,
+  "य": 105,
+  "र": 106,
+  "ऱ": 107,
+  "ल": 108,
+  "ळ": 109,
+  "व": 110,
+  "श": 111,
+  "ष": 112,
+  "स": 113,
+  "ह": 114,
+  "़": 115,
+  "ऽ": 116,
+  "ा": 117,
+  "ि": 118,
+  "ी": 119,
+  "ु": 120,
+  "ू": 121,
+  "ृ": 122,
+  "ॄ": 123,
+  "ॅ": 124,
+  "ॆ": 125,
+  "े": 126,
+  "ै": 127,
+  "ॉ": 128,
+  "ॊ": 129,
+  "ो": 130,
+  "ौ": 131,
+  "्": 132,
+  "॓": 133,
+  "॔": 134,
+  "क़": 135,
+  "ख़": 136,
+  "ग़": 137,
+  "ज़": 138,
+  "ड़": 139,
+  "ढ़": 140,
+  "फ़": 141,
+  "य़": 142,
+  "ॢ": 143,
+  "।": 144,
+  "॥": 145,
+  "ॲ": 146,
+  "–": 147,
+  "‘": 148,
+  "’": 149,
+  "“": 150,
+  "”": 151
+}