tokenizer_config.json

{
  "add_bos_token": false,
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<|SOT|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<|EOT|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "<|pad|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<|de-ch|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "<|transcribe|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|SOT|>",
    "<|EOT|>",
    "<|pad|>",
    "<|de-ch|>",
    "<|transcribe|>"
  ],
  "bos_token": "<|SOT|>",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|EOT|>",
  "errors": "replace",
  "model_max_length": 1024,
  "pad_token": "<|pad|>",
  "processor_class": "WhisperProcessor",
  "return_attention_mask": false,
  "tokenizer_class": "WhisperTokenizer",
  "unk_token": "<|SOT|>"
}