Commit
·
8300b28
1
Parent(s):
f855df7
Upload tokenizer
Browse files- special_tokens_map.json +6 -0
- tokenizer_config.json +11 -0
- vocab.json +9 -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 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 6,
|
| 3 |
+
"[UNK]": 5,
|
| 4 |
+
"s_c": 1,
|
| 5 |
+
"s_j": 3,
|
| 6 |
+
"s_n": 4,
|
| 7 |
+
"s_t": 0,
|
| 8 |
+
"|": 2
|
| 9 |
+
}
|