CoolFace
Modelpublic

dmusingu/luganda_wav2vec2_ctc_tokenizer

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes12downloads
tokenizer_config.json48 linesDownload Raw Back to root
1{2  "added_tokens_decoder": {3    "31": {4      "content": "[UNK]",5      "lstrip": true,6      "normalized": false,7      "rstrip": true,8      "single_word": false,9      "special": false10    },11    "32": {12      "content": "[PAD]",13      "lstrip": true,14      "normalized": false,15      "rstrip": true,16      "single_word": false,17      "special": false18    },19    "33": {20      "content": "<s>",21      "lstrip": false,22      "normalized": false,23      "rstrip": false,24      "single_word": false,25      "special": true26    },27    "34": {28      "content": "</s>",29      "lstrip": false,30      "normalized": false,31      "rstrip": false,32      "single_word": false,33      "special": true34    }35  },36  "bos_token": "<s>",37  "clean_up_tokenization_spaces": true,38  "do_lower_case": false,39  "eos_token": "</s>",40  "model_max_length": 1000000000000000019884624838656,41  "pad_token": "[PAD]",42  "replace_word_delimiter_char": " ",43  "target_lang": null,44  "tokenizer_class": "Wav2Vec2CTCTokenizer",45  "unk_token": "[UNK]",46  "word_delimiter_token": "|"47}48