Commit
•
8438981
1
Parent(s):
a393b4b
Upload tokenizer
Browse files- special_tokens_map.json +6 -0
- tokenizer_config.json +11 -0
- vocab.json +29 -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 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 26,
|
| 3 |
+
"[UNK]": 25,
|
| 4 |
+
"a_c": 18,
|
| 5 |
+
"a_j": 10,
|
| 6 |
+
"a_n": 22,
|
| 7 |
+
"a_t": 1,
|
| 8 |
+
"f_c": 13,
|
| 9 |
+
"f_j": 17,
|
| 10 |
+
"f_n": 8,
|
| 11 |
+
"f_t": 23,
|
| 12 |
+
"la_c": 15,
|
| 13 |
+
"la_j": 5,
|
| 14 |
+
"la_n": 7,
|
| 15 |
+
"la_t": 11,
|
| 16 |
+
"n_c": 4,
|
| 17 |
+
"n_j": 6,
|
| 18 |
+
"n_n": 2,
|
| 19 |
+
"n_t": 14,
|
| 20 |
+
"p_c": 0,
|
| 21 |
+
"p_j": 20,
|
| 22 |
+
"p_n": 16,
|
| 23 |
+
"p_t": 24,
|
| 24 |
+
"v_c": 21,
|
| 25 |
+
"v_j": 9,
|
| 26 |
+
"v_n": 3,
|
| 27 |
+
"v_t": 19,
|
| 28 |
+
"|": 12
|
| 29 |
+
}
|