Commit
•
8fbe597
1
Parent(s):
db2c968
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>": 65, "</s>": 66}
|
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, "অ": 4, "আ": 5, "ই": 6, "ঈ": 7, "উ": 8, "এ": 9, "ঐ": 10, "ও": 11, "ঔ": 12, "ক": 13, "খ": 14, "গ": 15, "ঘ": 16, "ঙ": 17, "চ": 18, "ছ": 19, "জ": 20, "ঞ": 21, "ট": 22, "ঠ": 23, "ড": 24, "ঢ": 25, "ণ": 26, "ত": 27, "থ": 28, "দ": 29, "ধ": 30, "ন": 31, "প": 32, "ফ": 33, "ব": 34, "ভ": 35, "ম": 36, "য": 37, "র": 38, "ল": 39, "শ": 40, "ষ": 41, "স": 42, "হ": 43, "়": 44, "া": 45, "ি": 46, "ী": 47, "ু": 48, "ূ": 49, "ৃ": 50, "ে": 51, "ৈ": 52, "ো": 53, "ৌ": 54, "্": 55, "ৎ": 56, "ড়": 57, "ঢ়": 58, "য়": 59, "ৰ": 60, "ৱ": 61, "’": 62, "|": 0, "[UNK]": 63, "[PAD]": 64}
|