Commit
•
78fa457
1
Parent(s):
790d7b1
Upload tokenizer
Browse files- added_tokens.json +4 -0
- special_tokens_map.json +16 -0
- tokenizer_config.json +1 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s>": 40,
|
| 3 |
+
"<s>": 39
|
| 4 |
+
}
|
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,20 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"eos_token": "</s>",
|
| 4 |
"pad_token": "[PAD]",
|
|
|
|
| 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]",
|
tokenizer_config.json
CHANGED
|
@@ -5,6 +5,7 @@
|
|
| 5 |
"eos_token": "</s>",
|
| 6 |
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
"pad_token": "[PAD]",
|
|
|
|
| 8 |
"replace_word_delimiter_char": " ",
|
| 9 |
"target_lang": null,
|
| 10 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
|
|
|
| 5 |
"eos_token": "</s>",
|
| 6 |
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
"pad_token": "[PAD]",
|
| 8 |
+
"processor_class": "Wav2Vec2Processor",
|
| 9 |
"replace_word_delimiter_char": " ",
|
| 10 |
"target_lang": null,
|
| 11 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|