{
  "vocab_size": 4192,
  "special_tokens": [
    "<pad>",
    "<unk>",
    "<bos>",
    "<eos>"
  ],
  "pad_id": 0,
  "unk_id": 1,
  "bos_id": 2,
  "eos_id": 3,
  "train_ratio": 0.8,
  "seed": 42,
  "languages": [
    "ml"
  ],
  "normalizer": "NFC",
  "pre_tokenizer": "ByteLevel",
  "recommended_seq_len": 768,
  "fertility_per_lang": {
    "ml": {
      "mean_fertility": 0.6979,
      "mean_tokens": 391.4,
      "p50_tokens": 394,
      "p90_tokens": 576,
      "p95_tokens": 688,
      "p99_tokens": 1086,
      "max_tokens": 1316
    }
  },
  "token_overlap": {
    "pairwise": {},
    "family_overlap": {
      "indo_aryan_vs_indo_aryan": {
        "shared_tokens": 0,
        "jaccard_similarity": 0
      },
      "dravidian_vs_indo_aryan": {
        "shared_tokens": 0,
        "jaccard_similarity": 0.0
      },
      "dravidian_vs_dravidian": {
        "shared_tokens": 3628,
        "jaccard_similarity": 1.0
      }
    },
    "per_lang_unique_tokens": {
      "ml": 3628
    }
  },
  "vocab_utilization": {
    "vocab_size": 4192,
    "used_tokens": 3628,
    "unused_tokens": 564,
    "utilization_rate": 0.8655,
    "shared_all_langs": 3628,
    "unique_per_lang": {
      "ml": 3628
    }
  },
  "oov_rates": {
    "ml": {
      "total_tokens": 880083,
      "unk_tokens": 0,
      "oov_rate": 0.0
    }
  }
}