Upload tokenizer
Browse files- special_tokens_map.json +6 -0
- tokenizer_config.json +11 -0
- vocab.json +26 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"unk_token": "[UNK]"
|
| 6 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"do_lower_case": false,
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"replace_word_delimiter_char": " ",
|
| 8 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 9 |
+
"unk_token": "[UNK]",
|
| 10 |
+
"word_delimiter_token": "|"
|
| 11 |
+
}
|
vocab.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"A": 1,
|
| 3 |
+
"B": 2,
|
| 4 |
+
"C": 3,
|
| 5 |
+
"D": 4,
|
| 6 |
+
"E": 5,
|
| 7 |
+
"F": 6,
|
| 8 |
+
"G": 7,
|
| 9 |
+
"H": 8,
|
| 10 |
+
"I": 9,
|
| 11 |
+
"K": 10,
|
| 12 |
+
"L": 11,
|
| 13 |
+
"M": 12,
|
| 14 |
+
"N": 13,
|
| 15 |
+
"O": 14,
|
| 16 |
+
"P": 15,
|
| 17 |
+
"R": 16,
|
| 18 |
+
"S": 17,
|
| 19 |
+
"T": 18,
|
| 20 |
+
"U": 19,
|
| 21 |
+
"W": 20,
|
| 22 |
+
"Y": 21,
|
| 23 |
+
"[PAD]": 23,
|
| 24 |
+
"[UNK]": 22,
|
| 25 |
+
"|": 0
|
| 26 |
+
}
|