Upload tokenizer
Browse files- tokenizer_config.json +35 -0
tokenizer_config.json
CHANGED
|
@@ -1,4 +1,38 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"clean_up_tokenization_spaces": true,
|
| 4 |
"do_lower_case": false,
|
|
@@ -6,6 +40,7 @@
|
|
| 6 |
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
"pad_token": "[PAD]",
|
| 8 |
"replace_word_delimiter_char": " ",
|
|
|
|
| 9 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 10 |
"unk_token": "[UNK]",
|
| 11 |
"word_delimiter_token": "|"
|
|
|
|
| 1 |
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"51": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": true,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": true,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": false
|
| 10 |
+
},
|
| 11 |
+
"52": {
|
| 12 |
+
"content": "[PAD]",
|
| 13 |
+
"lstrip": true,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": true,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": false
|
| 18 |
+
},
|
| 19 |
+
"53": {
|
| 20 |
+
"content": "<s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"54": {
|
| 28 |
+
"content": "</s>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
"bos_token": "<s>",
|
| 37 |
"clean_up_tokenization_spaces": true,
|
| 38 |
"do_lower_case": false,
|
|
|
|
| 40 |
"model_max_length": 1000000000000000019884624838656,
|
| 41 |
"pad_token": "[PAD]",
|
| 42 |
"replace_word_delimiter_char": " ",
|
| 43 |
+
"target_lang": null,
|
| 44 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 45 |
"unk_token": "[UNK]",
|
| 46 |
"word_delimiter_token": "|"
|