Upload tokenizer

README.md

@@ -1,10 +1,10 @@
 ---
-license: mit
 base_model: facebook/w2v-bert-2.0
-tags:
-- generated_from_trainer
+license: mit
 metrics:
 - wer
+tags:
+- generated_from_trainer
 model-index:
 - name: malayalam_combined_
   results: []

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 93,
+  "<s>": 92
+}

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": {
+    "90": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "93": {
+      "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]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,94 @@
+{
+  "*": 1,
+  "0": 2,
+  "1": 3,
+  "2": 4,
+  "3": 5,
+  "4": 6,
+  "5": 7,
+  "6": 8,
+  "7": 9,
+  "8": 10,
+  "9": 11,
+  "=": 12,
+  "@": 13,
+  "[PAD]": 91,
+  "[UNK]": 90,
+  "|": 0,
+  "ം": 14,
+  "ഃ": 15,
+  "അ": 16,
+  "ആ": 17,
+  "ഇ": 18,
+  "ഈ": 19,
+  "ഉ": 20,
+  "ഊ": 21,
+  "ഋ": 22,
+  "എ": 23,
+  "ഏ": 24,
+  "ഐ": 25,
+  "ഒ": 26,
+  "ഓ": 27,
+  "ഔ": 28,
+  "ക": 29,
+  "ഖ": 30,
+  "ഗ": 31,
+  "ഘ": 32,
+  "ങ": 33,
+  "ച": 34,
+  "ഛ": 35,
+  "ജ": 36,
+  "ഝ": 37,
+  "ഞ": 38,
+  "ട": 39,
+  "ഠ": 40,
+  "ഡ": 41,
+  "ഢ": 42,
+  "ണ": 43,
+  "ത": 44,
+  "ഥ": 45,
+  "ദ": 46,
+  "ധ": 47,
+  "ന": 48,
+  "പ": 49,
+  "ഫ": 50,
+  "ബ": 51,
+  "ഭ": 52,
+  "മ": 53,
+  "യ": 54,
+  "ര": 55,
+  "റ": 56,
+  "ല": 57,
+  "ള": 58,
+  "ഴ": 59,
+  "വ": 60,
+  "ശ": 61,
+  "ഷ": 62,
+  "സ": 63,
+  "ഹ": 64,
+  "ാ": 65,
+  "ി": 66,
+  "ീ": 67,
+  "ു": 68,
+  "ൂ": 69,
+  "ൃ": 70,
+  "െ": 71,
+  "േ": 72,
+  "ൈ": 73,
+  "ൊ": 74,
+  "ോ": 75,
+  "ൌ": 76,
+  "്": 77,
+  "ൗ": 78,
+  "൦": 79,
+  "൨": 80,
+  "൪": 81,
+  "ൺ": 82,
+  "ൻ": 83,
+  "ർ": 84,
+  "ൽ": 85,
+  "ൾ": 86,
+  "‌": 87,
+  "‍": 88,
+  "’": 89
+}