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>": 68, "</s>": 69}
|
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 |
+
{"জ": 0, "া": 1, "উ": 2, "ৃ": 3, "ছ": 4, "ই": 5, "র": 6, "ঐ": 7, "়": 8, "ঁ": 9, "ও": 10, "ঈ": 11, "ে": 12, "ি": 13, "অ": 14, "ঝ": 15, "ৈ": 16, "ঃ": 17, "এ": 18, "ম": 19, "ং": 20, "ব": 21, "আ": 22, "ৌ": 23, "ট": 24, "ূ": 25, "ষ": 26, "ড়": 27, "হ": 28, "ৎ": 29, "গ": 30, "য়": 31, "ঢ": 32, "ী": 33, "ু": 34, "ফ": 35, "ন": 36, "ল": 37, "ঠ": 38, "খ": 39, "ণ": 40, "।": 41, "চ": 43, "ৰ": 44, "ড": 45, "'": 46, "ঔ": 47, "প": 48, "ক": 49, "ঞ": 50, "’": 51, "ত": 52, "্": 53, "স": 54, "য": 55, "ঢ়": 56, "ঘ": 57, "ঙ": 58, "ধ": 59, "ৱ": 60, "থ": 61, "ভ": 62, "দ": 63, "শ": 64, "ো": 65, "|": 42, "[UNK]": 66, "[PAD]": 67}
|