Commit
•
46fe0a4
1
Parent(s):
35c510e
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>": 66, "</s>": 67}
|
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, "ঁ": 2, "ং": 3, "ঃ": 4, "অ": 5, "আ": 6, "ই": 7, "ঈ": 8, "উ": 9, "এ": 10, "ঐ": 11, "ও": 12, "ঔ": 13, "ক": 14, "খ": 15, "গ": 16, "ঘ": 17, "ঙ": 18, "চ": 19, "ছ": 20, "জ": 21, "ঝ": 22, "ঞ": 23, "ট": 24, "ঠ": 25, "ড": 26, "ঢ": 27, "ণ": 28, "ত": 29, "থ": 30, "দ": 31, "ধ": 32, "ন": 33, "প": 34, "ফ": 35, "ব": 36, "ভ": 37, "ম": 38, "য": 39, "র": 40, "ল": 41, "শ": 42, "ষ": 43, "স": 44, "হ": 45, "়": 46, "া": 47, "ি": 48, "ী": 49, "ু": 50, "ূ": 51, "ৃ": 52, "ে": 53, "ৈ": 54, "ো": 55, "ৌ": 56, "্": 57, "ৎ": 58, "ড়": 59, "ঢ়": 60, "য়": 61, "ৰ": 62, "ৱ": 63, "|": 0, "[UNK]": 64, "[PAD]": 65}
|