Upload tokenizer
Browse files- added_tokens.json +4 -0
- special_tokens_map.json +2 -2
- tokenizer_config.json +22 -6
- vocab.json +4 -4
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s>": 33,
|
| 3 |
+
"<s>": 32
|
| 4 |
+
}
|
special_tokens_map.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"eos_token": "</s>",
|
| 4 |
-
"pad_token": "<
|
| 5 |
-
"unk_token": "<
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<PAD>",
|
| 5 |
+
"unk_token": "<UNK>"
|
| 6 |
}
|
tokenizer_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
-
"content": "<
|
| 5 |
"lstrip": true,
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": true,
|
|
@@ -9,7 +9,7 @@
|
|
| 9 |
"special": false
|
| 10 |
},
|
| 11 |
"1": {
|
| 12 |
-
"content": "<
|
| 13 |
"lstrip": true,
|
| 14 |
"normalized": false,
|
| 15 |
"rstrip": true,
|
|
@@ -17,7 +17,7 @@
|
|
| 17 |
"special": false
|
| 18 |
},
|
| 19 |
"2": {
|
| 20 |
-
"content": "</
|
| 21 |
"lstrip": true,
|
| 22 |
"normalized": false,
|
| 23 |
"rstrip": true,
|
|
@@ -25,12 +25,28 @@
|
|
| 25 |
"special": false
|
| 26 |
},
|
| 27 |
"3": {
|
| 28 |
-
"content": "<
|
| 29 |
"lstrip": true,
|
| 30 |
"normalized": false,
|
| 31 |
"rstrip": true,
|
| 32 |
"single_word": false,
|
| 33 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
}
|
| 35 |
},
|
| 36 |
"bos_token": "<s>",
|
|
@@ -38,10 +54,10 @@
|
|
| 38 |
"do_lower_case": false,
|
| 39 |
"eos_token": "</s>",
|
| 40 |
"model_max_length": 1000000000000000019884624838656,
|
| 41 |
-
"pad_token": "<
|
| 42 |
"replace_word_delimiter_char": " ",
|
| 43 |
"target_lang": null,
|
| 44 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 45 |
-
"unk_token": "<
|
| 46 |
"word_delimiter_token": "|"
|
| 47 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
+
"content": "<PAD>",
|
| 5 |
"lstrip": true,
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": true,
|
|
|
|
| 9 |
"special": false
|
| 10 |
},
|
| 11 |
"1": {
|
| 12 |
+
"content": "<S>",
|
| 13 |
"lstrip": true,
|
| 14 |
"normalized": false,
|
| 15 |
"rstrip": true,
|
|
|
|
| 17 |
"special": false
|
| 18 |
},
|
| 19 |
"2": {
|
| 20 |
+
"content": "</S>",
|
| 21 |
"lstrip": true,
|
| 22 |
"normalized": false,
|
| 23 |
"rstrip": true,
|
|
|
|
| 25 |
"special": false
|
| 26 |
},
|
| 27 |
"3": {
|
| 28 |
+
"content": "<UNK>",
|
| 29 |
"lstrip": true,
|
| 30 |
"normalized": false,
|
| 31 |
"rstrip": true,
|
| 32 |
"single_word": false,
|
| 33 |
"special": false
|
| 34 |
+
},
|
| 35 |
+
"32": {
|
| 36 |
+
"content": "<s>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"33": {
|
| 44 |
+
"content": "</s>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
}
|
| 51 |
},
|
| 52 |
"bos_token": "<s>",
|
|
|
|
| 54 |
"do_lower_case": false,
|
| 55 |
"eos_token": "</s>",
|
| 56 |
"model_max_length": 1000000000000000019884624838656,
|
| 57 |
+
"pad_token": "<PAD>",
|
| 58 |
"replace_word_delimiter_char": " ",
|
| 59 |
"target_lang": null,
|
| 60 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 61 |
+
"unk_token": "<UNK>",
|
| 62 |
"word_delimiter_token": "|"
|
| 63 |
}
|
vocab.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"'": 27,
|
| 3 |
-
"</
|
| 4 |
-
"<
|
| 5 |
-
"<
|
| 6 |
-
"<
|
| 7 |
"A": 7,
|
| 8 |
"B": 24,
|
| 9 |
"C": 19,
|
|
|
|
| 1 |
{
|
| 2 |
"'": 27,
|
| 3 |
+
"</S>": 2,
|
| 4 |
+
"<PAD>": 0,
|
| 5 |
+
"<S>": 1,
|
| 6 |
+
"<UNK>": 3,
|
| 7 |
"A": 7,
|
| 8 |
"B": 24,
|
| 9 |
"C": 19,
|