tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "<s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "</s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "<unk>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Whitespace"
  },
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<pad>": 0,
      "<s>": 1,
      "</s>": 2,
      "<unk>": 3,
      "Kerala": 4,
      "classical": 5,
      "arts": 6,
      "Kathakali": 7,
      "Mohiniyattam": 8,
      "Koodiyattam": 9,
      "Theyyam": 10,
      "culture": 11,
      "heritage": 12,
      "Malayalam": 13,
      "English": 14,
      "performance": 15,
      "music": 16,
      "dance": 17,
      "temple": 18,
      "tradition": 19
    },
    "unk_token": "<unk>"
  }
}