Upload tokenizer
Browse files- tokenizer_config.json +1 -1
- vocab.json +2 -2
tokenizer_config.json
CHANGED
|
@@ -43,5 +43,5 @@
|
|
| 43 |
"target_lang": null,
|
| 44 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 45 |
"unk_token": "[UNK]",
|
| 46 |
-
"word_delimiter_token": "
|
| 47 |
}
|
|
|
|
| 43 |
"target_lang": null,
|
| 44 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 45 |
"unk_token": "[UNK]",
|
| 46 |
+
"word_delimiter_token": " "
|
| 47 |
}
|
vocab.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"[PAD]": 28,
|
| 3 |
"[UNK]": 27,
|
| 4 |
"a": 1,
|
|
@@ -26,6 +27,5 @@
|
|
| 26 |
"w": 23,
|
| 27 |
"x": 24,
|
| 28 |
"y": 25,
|
| 29 |
-
"z": 26
|
| 30 |
-
"|": 0
|
| 31 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
" ": 0,
|
| 3 |
"[PAD]": 28,
|
| 4 |
"[UNK]": 27,
|
| 5 |
"a": 1,
|
|
|
|
| 27 |
"w": 23,
|
| 28 |
"x": 24,
|
| 29 |
"y": 25,
|
| 30 |
+
"z": 26
|
|
|
|
| 31 |
}
|