Commit
•
14756b5
1
Parent(s):
3e7fb9d
add tokenizer
Browse files- added_tokens.json +1 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
added_tokens.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"<s>": 54, "</s>": 55}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
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": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"ّ": 1, "ހ": 2, "ށ": 3, "ނ": 4, "ރ": 5, "ބ": 6, "ޅ": 7, "ކ": 8, "އ": 9, "ވ": 10, "މ": 11, "ފ": 12, "ދ": 13, "ތ": 14, "ލ": 15, "ގ": 16, "ޏ": 17, "ސ": 18, "ޑ": 19, "ޒ": 20, "ޓ": 21, "ޔ": 22, "ޕ": 23, "ޖ": 24, "ޗ": 25, "ޘ": 26, "ޙ": 27, "ޚ": 28, "ޛ": 29, "ޝ": 30, "ޞ": 31, "ޟ": 32, "ޠ": 33, "ޡ": 34, "ޢ": 35, "ޣ": 36, "ޤ": 37, "ޥ": 38, "ަ": 39, "ާ": 40, "ި": 41, "ީ": 42, "ު": 43, "ޫ": 44, "ެ": 45, "ޭ": 46, "ޮ": 47, "ޯ": 48, "ް": 49, "ﷲ": 50, "ﷺ": 51, "|": 0, "[UNK]": 52, "[PAD]": 53}
|