add tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"ც": 0, "რ": 2, "კ": 3, "ჩ": 4, "ქ": 5, "ტ": 6, "ჭ": 7, "„": 8, "უ": 9, "ა": 10, "ღ": 11, "ნ": 12, "ჟ": 13, "ი": 14, "პ": 15, "ძ": 16, "თ": 17, "ვ": 18, "ო": 19, "ფ": 20, "წ": 21, "ლ": 22, "ს": 23, "ე": 24, "ხ": 25, "ჯ": 26, "–": 27, "ყ": 28, "ბ": 29, "ზ": 30, "მ": 31, "შ": 32, "გ": 33, "ჰ": 34, "დ": 35, "|": 1, "[UNK]": 36, "[PAD]": 37}
|