Upload tokenizer
Browse files- README.md +4 -4
- added_tokens.json +2 -2
- tokenizer_config.json +4 -4
- vocab.json +49 -48
README.md
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
---
|
2 |
license: cc-by-nc-4.0
|
3 |
-
base_model: utter-project/mHuBERT-147
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
6 |
datasets:
|
7 |
- common_voice_15_0
|
8 |
metrics:
|
@@ -11,8 +11,8 @@ model-index:
|
|
11 |
- name: mHuBERT-147-br
|
12 |
results:
|
13 |
- task:
|
14 |
-
name: Automatic Speech Recognition
|
15 |
type: automatic-speech-recognition
|
|
|
16 |
dataset:
|
17 |
name: common_voice_15_0
|
18 |
type: common_voice_15_0
|
@@ -20,9 +20,9 @@ model-index:
|
|
20 |
split: None
|
21 |
args: br
|
22 |
metrics:
|
23 |
-
-
|
24 |
-
type: wer
|
25 |
value: 53.76572908956329
|
|
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
1 |
---
|
2 |
license: cc-by-nc-4.0
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
+
base_model: utter-project/mHuBERT-147
|
6 |
datasets:
|
7 |
- common_voice_15_0
|
8 |
metrics:
|
|
|
11 |
- name: mHuBERT-147-br
|
12 |
results:
|
13 |
- task:
|
|
|
14 |
type: automatic-speech-recognition
|
15 |
+
name: Automatic Speech Recognition
|
16 |
dataset:
|
17 |
name: common_voice_15_0
|
18 |
type: common_voice_15_0
|
|
|
20 |
split: None
|
21 |
args: br
|
22 |
metrics:
|
23 |
+
- type: wer
|
|
|
24 |
value: 53.76572908956329
|
25 |
+
name: Wer
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
added_tokens.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
-
"</s>":
|
3 |
-
"<s>":
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"</s>": 50,
|
3 |
+
"<s>": 49
|
4 |
}
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
-
"
|
4 |
"content": "[UNK]",
|
5 |
"lstrip": true,
|
6 |
"normalized": false,
|
@@ -8,7 +8,7 @@
|
|
8 |
"single_word": false,
|
9 |
"special": false
|
10 |
},
|
11 |
-
"
|
12 |
"content": "[PAD]",
|
13 |
"lstrip": true,
|
14 |
"normalized": false,
|
@@ -16,7 +16,7 @@
|
|
16 |
"single_word": false,
|
17 |
"special": false
|
18 |
},
|
19 |
-
"
|
20 |
"content": "<s>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
@@ -24,7 +24,7 @@
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
"content": "</s>",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
+
"47": {
|
4 |
"content": "[UNK]",
|
5 |
"lstrip": true,
|
6 |
"normalized": false,
|
|
|
8 |
"single_word": false,
|
9 |
"special": false
|
10 |
},
|
11 |
+
"48": {
|
12 |
"content": "[PAD]",
|
13 |
"lstrip": true,
|
14 |
"normalized": false,
|
|
|
16 |
"single_word": false,
|
17 |
"special": false
|
18 |
},
|
19 |
+
"49": {
|
20 |
"content": "<s>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"50": {
|
28 |
"content": "</s>",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
vocab.json
CHANGED
@@ -1,50 +1,51 @@
|
|
1 |
{
|
2 |
-
"'":
|
3 |
-
"3":
|
4 |
-
"
|
5 |
-
"[
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
30 |
-
"
|
31 |
-
"
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
43 |
-
"
|
44 |
-
"
|
45 |
-
"
|
46 |
-
"
|
47 |
-
"
|
48 |
-
"
|
49 |
-
"
|
|
|
50 |
}
|
|
|
1 |
{
|
2 |
+
"'": 31,
|
3 |
+
"3": 15,
|
4 |
+
"X": 25,
|
5 |
+
"[PAD]": 48,
|
6 |
+
"[UNK]": 47,
|
7 |
+
"a": 14,
|
8 |
+
"b": 23,
|
9 |
+
"c": 5,
|
10 |
+
"d": 27,
|
11 |
+
"e": 24,
|
12 |
+
"f": 16,
|
13 |
+
"g": 29,
|
14 |
+
"h": 1,
|
15 |
+
"i": 45,
|
16 |
+
"j": 35,
|
17 |
+
"k": 9,
|
18 |
+
"l": 36,
|
19 |
+
"m": 22,
|
20 |
+
"n": 42,
|
21 |
+
"o": 17,
|
22 |
+
"p": 21,
|
23 |
+
"q": 28,
|
24 |
+
"r": 10,
|
25 |
+
"s": 46,
|
26 |
+
"t": 37,
|
27 |
+
"u": 0,
|
28 |
+
"v": 34,
|
29 |
+
"w": 12,
|
30 |
+
"x": 8,
|
31 |
+
"y": 43,
|
32 |
+
"z": 33,
|
33 |
+
"|": 26,
|
34 |
+
"à": 11,
|
35 |
+
"á": 19,
|
36 |
+
"â": 39,
|
37 |
+
"ã": 30,
|
38 |
+
"ç": 40,
|
39 |
+
"è": 38,
|
40 |
+
"é": 32,
|
41 |
+
"ê": 4,
|
42 |
+
"ë": 41,
|
43 |
+
"ñ": 13,
|
44 |
+
"ô": 18,
|
45 |
+
"ö": 3,
|
46 |
+
"ø": 7,
|
47 |
+
"ù": 44,
|
48 |
+
"û": 6,
|
49 |
+
"ü": 2,
|
50 |
+
"ı": 20
|
51 |
}
|