Upload tokenizer
Browse files- README.md +1 -1
- tokenizer_config.json +2 -2
- vocab.json +36 -36
README.md
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model: facebook/wav2vec2-large-xlsr-53
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
6 |
metrics:
|
7 |
- wer
|
8 |
model-index:
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
+
base_model: facebook/wav2vec2-large-xlsr-53
|
6 |
metrics:
|
7 |
- wer
|
8 |
model-index:
|
tokenizer_config.json
CHANGED
@@ -19,7 +19,7 @@
|
|
19 |
"40": {
|
20 |
"content": "<s>",
|
21 |
"lstrip": false,
|
22 |
-
"normalized":
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
@@ -27,7 +27,7 @@
|
|
27 |
"41": {
|
28 |
"content": "</s>",
|
29 |
"lstrip": false,
|
30 |
-
"normalized":
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
|
|
19 |
"40": {
|
20 |
"content": "<s>",
|
21 |
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
|
|
27 |
"41": {
|
28 |
"content": "</s>",
|
29 |
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
vocab.json
CHANGED
@@ -1,42 +1,42 @@
|
|
1 |
{
|
2 |
-
"'":
|
3 |
"[PAD]": 39,
|
4 |
"[UNK]": 38,
|
5 |
-
"a":
|
6 |
-
"b":
|
7 |
-
"c":
|
8 |
-
"d":
|
9 |
-
"e":
|
10 |
-
"f":
|
11 |
-
"g":
|
12 |
-
"h":
|
13 |
"i": 29,
|
14 |
-
"j":
|
15 |
-
"k":
|
16 |
-
"l":
|
17 |
-
"m":
|
18 |
-
"n":
|
19 |
-
"o":
|
20 |
-
"p":
|
21 |
-
"q":
|
22 |
-
"r":
|
23 |
-
"s":
|
24 |
-
"t":
|
25 |
-
"u":
|
26 |
-
"v":
|
27 |
-
"w":
|
28 |
-
"x":
|
29 |
"y": 3,
|
30 |
-
"z":
|
31 |
-
"|":
|
32 |
-
"à":
|
33 |
-
"â":
|
34 |
-
"è":
|
35 |
-
"é":
|
36 |
-
"ê":
|
37 |
-
"ñ":
|
38 |
-
"ô":
|
39 |
-
"ù":
|
40 |
-
"û":
|
41 |
-
"ü":
|
42 |
}
|
|
|
1 |
{
|
2 |
+
"'": 17,
|
3 |
"[PAD]": 39,
|
4 |
"[UNK]": 38,
|
5 |
+
"a": 12,
|
6 |
+
"b": 14,
|
7 |
+
"c": 7,
|
8 |
+
"d": 15,
|
9 |
+
"e": 0,
|
10 |
+
"f": 21,
|
11 |
+
"g": 2,
|
12 |
+
"h": 9,
|
13 |
"i": 29,
|
14 |
+
"j": 37,
|
15 |
+
"k": 11,
|
16 |
+
"l": 30,
|
17 |
+
"m": 13,
|
18 |
+
"n": 32,
|
19 |
+
"o": 24,
|
20 |
+
"p": 25,
|
21 |
+
"q": 27,
|
22 |
+
"r": 1,
|
23 |
+
"s": 23,
|
24 |
+
"t": 22,
|
25 |
+
"u": 20,
|
26 |
+
"v": 28,
|
27 |
+
"w": 5,
|
28 |
+
"x": 4,
|
29 |
"y": 3,
|
30 |
+
"z": 31,
|
31 |
+
"|": 8,
|
32 |
+
"à": 34,
|
33 |
+
"â": 26,
|
34 |
+
"è": 33,
|
35 |
+
"é": 35,
|
36 |
+
"ê": 16,
|
37 |
+
"ñ": 6,
|
38 |
+
"ô": 10,
|
39 |
+
"ù": 36,
|
40 |
+
"û": 18,
|
41 |
+
"ü": 19
|
42 |
}
|