Commit
•
b836c3f
1
Parent(s):
c7336e4
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>": 50, "</s>": 51}
|
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 |
+
{"ஃ": 1, "அ": 2, "ஆ": 3, "இ": 4, "ஈ": 5, "உ": 6, "ஊ": 7, "எ": 8, "ஏ": 9, "ஐ": 10, "ஒ": 11, "ஓ": 12, "ஔ": 13, "க": 14, "ங": 15, "ச": 16, "ஜ": 17, "ஞ": 18, "ட": 19, "ண": 20, "த": 21, "ந": 22, "ன": 23, "ப": 24, "ம": 25, "ய": 26, "ர": 27, "ற": 28, "ல": 29, "ள": 30, "ழ": 31, "வ": 32, "ஷ": 33, "ஸ": 34, "ஹ": 35, "ா": 36, "ி": 37, "ீ": 38, "ு": 39, "ூ": 40, "ெ": 41, "ே": 42, "ை": 43, "ொ": 44, "ோ": 45, "ௌ": 46, "்": 47, "|": 0, "[UNK]": 48, "[PAD]": 49}
|