Upload tokenizer
Browse files- tokenizer.json +9 -0
- tokenizer_config.json +8 -0
tokenizer.json
CHANGED
@@ -21,6 +21,15 @@
|
|
21 |
"normalized": false,
|
22 |
"special": true
|
23 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
{
|
25 |
"id": 3,
|
26 |
"content": "UTT_BOUNDARY",
|
|
|
21 |
"normalized": false,
|
22 |
"special": true
|
23 |
},
|
24 |
+
{
|
25 |
+
"id": 2,
|
26 |
+
"content": "WORD_BOUNDARY",
|
27 |
+
"single_word": false,
|
28 |
+
"lstrip": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"special": true
|
32 |
+
},
|
33 |
{
|
34 |
"id": 3,
|
35 |
"content": "UTT_BOUNDARY",
|
tokenizer_config.json
CHANGED
@@ -17,6 +17,14 @@
|
|
17 |
"single_word": false,
|
18 |
"special": true
|
19 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
"3": {
|
21 |
"content": "UTT_BOUNDARY",
|
22 |
"lstrip": false,
|
|
|
17 |
"single_word": false,
|
18 |
"special": true
|
19 |
},
|
20 |
+
"2": {
|
21 |
+
"content": "WORD_BOUNDARY",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
"3": {
|
29 |
"content": "UTT_BOUNDARY",
|
30 |
"lstrip": false,
|