merge
Browse files- added_tokens.json +1 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +5 -1
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<s>": 73, "</s>": 74}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0ba956e9839aa07016519fdfa526ee53a8b6a22d5f2e4b17268e9859f128846
|
3 |
+
size 1262231153
|
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
CHANGED
@@ -1 +1,5 @@
|
|
1 |
-
|
|
|
|
|
|
|
|
|
|
1 |
+
<<<<<<< HEAD
|
2 |
+
{"\u1780": 1, "\u1781": 2, "\u1782": 3, "\u1783": 4, "\u1784": 5, "\u1785": 6, "\u1786": 7, "\u1787": 8, "\u1788": 9, "\u1789": 10, "\u178a": 11, "\u178b": 12, "\u178c": 13, "\u178d": 14, "\u178e": 15, "\u178f": 16, "\u1790": 17, "\u1791": 18, "\u1792": 19, "\u1793": 20, "\u1794": 21, "\u1795": 22, "\u1796": 23, "\u1797": 24, "\u1798": 25, "\u1799": 26, "\u179a": 27, "\u179b": 28, "\u179c": 29, "\u179f": 30, "\u17a0": 31, "\u17a1": 32, "\u17a2": 33, "\u17a5": 34, "\u17a7": 35, "\u17aa": 36, "\u17ab": 37, "\u17ac": 38, "\u17ad": 39, "\u17ae": 40, "\u17af": 41, "\u17b1": 42, "\u17b6": 43, "\u17b7": 44, "\u17b8": 45, "\u17b9": 46, "\u17ba": 47, "\u17bb": 48, "\u17bc": 49, "\u17bd": 50, "\u17be": 51, "\u17bf": 52, "\u17c0": 53, "\u17c1": 54, "\u17c2": 55, "\u17c3": 56, "\u17c4": 57, "\u17c5": 58, "\u17c6": 59, "\u17c7": 60, "\u17c8": 61, "\u17c9": 62, "\u17ca": 63, "\u17cb": 64, "\u17cc": 65, "\u17cd": 66, "\u17ce": 67, "\u17cf": 68, "\u17d0": 69, "\u17d2": 70, "|": 0, "[UNK]": 71, "[PAD]": 72}
|
3 |
+
=======
|
4 |
+
{"แ": 1, "แ": 2, "แ": 3, "แ": 4, "แ": 5, "แ
": 6, "แ": 7, "แ": 8, "แ": 9, "แ": 10, "แ": 11, "แ": 12, "แ": 13, "แ": 14, "แ": 15, "แ": 16, "แ": 17, "แ": 18, "แ": 19, "แ": 20, "แ": 21, "แ": 22, "แ": 23, "แ": 24, "แ": 25, "แ": 26, "แ": 27, "แ": 28, "แ": 29, "แ": 30, "แ ": 31, "แก": 32, "แข": 33, "แฅ": 34, "แง": 35, "แช": 36, "แซ": 37, "แฌ": 38, "แญ": 39, "แฎ": 40, "แฏ": 41, "แฑ": 42, "แถ": 43, "แท": 44, "แธ": 45, "แน": 46, "แบ": 47, "แป": 48, "แผ": 49, "แฝ": 50, "แพ": 51, "แฟ": 52, "แ": 53, "แ": 54, "แ": 55, "แ": 56, "แ": 57, "แ
": 58, "แ": 59, "แ": 60, "แ": 61, "แ": 62, "แ": 63, "แ": 64, "แ": 65, "แ": 66, "แ": 67, "แ": 68, "แ": 69, "แ": 70, "|": 0, "[UNK]": 71, "[PAD]": 72}
|
5 |
+
>>>>>>> dff1f3008b5c2afbbbcab722e17fded4bf8f782b
|