Commit
•
09686e9
1
Parent(s):
c7abc93
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>": 67, "</s>": 68}
|
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": "/workspace/Assamese_Wav2Vec/", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"'": 1, "-": 2, "ঁ": 3, "ং": 4, "ঃ": 5, "অ": 6, "আ": 7, "ই": 8, "ঈ": 9, "উ": 10, "এ": 11, "ঐ": 12, "ও": 13, "ঔ": 14, "ক": 15, "খ": 16, "গ": 17, "ঘ": 18, "ঙ": 19, "চ": 20, "ছ": 21, "জ": 22, "ঝ": 23, "ঞ": 24, "ট": 25, "ঠ": 26, "ড": 27, "ঢ": 28, "ণ": 29, "ত": 30, "থ": 31, "দ": 32, "ধ": 33, "ন": 34, "প": 35, "ফ": 36, "ব": 37, "ভ": 38, "ম": 39, "য": 40, "র": 41, "ল": 42, "শ": 43, "ষ": 44, "স": 45, "হ": 46, "়": 47, "া": 48, "ি": 49, "ী": 50, "ু": 51, "ূ": 52, "ৃ": 53, "ে": 54, "ৈ": 55, "ো": 56, "ৌ": 57, "্": 58, "ৎ": 59, "ড়": 60, "ঢ়": 61, "য়": 62, "ৰ": 63, "ৱ": 64, "^": 0, "[UNK]": 65, "[PAD]": 66}
|