w2v-bert-2.0-gl / tokenizer.json
avladu's picture
Replace incomplete model with complete w2v-BERT CTC checkpoint
3d09a7b verified
Raw History Blame Contribute Delete
837 Bytes
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [],
"normalizer": null,
"pre_tokenizer": {
"type": "Whitespace"
},
"post_processor": null,
"decoder": null,
"model": {
"type": "WordLevel",
"vocab": {
"|": 0,
"a": 1,
"b": 2,
"c": 3,
"d": 4,
"e": 5,
"f": 6,
"g": 7,
"h": 8,
"i": 9,
"j": 10,
"k": 11,
"l": 12,
"m": 13,
"n": 14,
"o": 15,
"p": 16,
"q": 17,
"r": 18,
"s": 19,
"t": 20,
"u": 21,
"v": 22,
"w": 23,
"x": 24,
"y": 25,
"z": 26,
"á": 27,
"ç": 28,
"é": 29,
"í": 30,
"ñ": 31,
"ó": 32,
"ú": 33,
"[UNK]": 34,
"[PAD]": 35
},
"unk_token": "[UNK]"
}
}