Upload tokenizer
Browse files- added_tokens.json +3 -1
- special_tokens_map.json +0 -16
- tokenizer_config.json +36 -0
added_tokens.json
CHANGED
|
@@ -1,4 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"</s>": 56,
|
| 3 |
-
"<s>": 55
|
|
|
|
|
|
|
| 4 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"</s>": 56,
|
| 3 |
+
"<s>": 55,
|
| 4 |
+
"[PAD]": 54,
|
| 5 |
+
"[UNK]": 53
|
| 6 |
}
|
special_tokens_map.json
CHANGED
|
@@ -1,20 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
{
|
| 4 |
-
"content": "<s>",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": true,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false
|
| 9 |
-
},
|
| 10 |
-
{
|
| 11 |
-
"content": "</s>",
|
| 12 |
-
"lstrip": false,
|
| 13 |
-
"normalized": true,
|
| 14 |
-
"rstrip": false,
|
| 15 |
-
"single_word": false
|
| 16 |
-
}
|
| 17 |
-
],
|
| 18 |
"bos_token": "<s>",
|
| 19 |
"eos_token": "</s>",
|
| 20 |
"pad_token": "[PAD]",
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"eos_token": "</s>",
|
| 4 |
"pad_token": "[PAD]",
|
tokenizer_config.json
CHANGED
|
@@ -1,4 +1,39 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"clean_up_tokenization_spaces": true,
|
| 4 |
"do_lower_case": false,
|
|
@@ -8,6 +43,7 @@
|
|
| 8 |
"replace_word_delimiter_char": " ",
|
| 9 |
"target_lang": null,
|
| 10 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
|
|
|
| 11 |
"unk_token": "[UNK]",
|
| 12 |
"word_delimiter_token": "|"
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"53": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": true,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": true,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": false
|
| 10 |
+
},
|
| 11 |
+
"54": {
|
| 12 |
+
"content": "[PAD]",
|
| 13 |
+
"lstrip": true,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": true,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": false
|
| 18 |
+
},
|
| 19 |
+
"55": {
|
| 20 |
+
"content": "<s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"56": {
|
| 28 |
+
"content": "</s>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"additional_special_tokens": [],
|
| 37 |
"bos_token": "<s>",
|
| 38 |
"clean_up_tokenization_spaces": true,
|
| 39 |
"do_lower_case": false,
|
|
|
|
| 43 |
"replace_word_delimiter_char": " ",
|
| 44 |
"target_lang": null,
|
| 45 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 46 |
+
"tokenizer_file": null,
|
| 47 |
"unk_token": "[UNK]",
|
| 48 |
"word_delimiter_token": "|"
|
| 49 |
}
|