batoula187
commited on
Commit
•
8efa8b9
1
Parent(s):
62d578c
Upload tokenizer
Browse files- README.md +4 -4
- added_tokens.json +2 -2
- tokenizer_config.json +4 -4
- vocab.json +88 -65
README.md
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
---
|
2 |
-
base_model: batoula187/wav2vec2-large-xls-r-300m-arabic-colab
|
3 |
tags:
|
4 |
- generated_from_trainer
|
|
|
5 |
datasets:
|
6 |
- common_voice_12_0
|
7 |
metrics:
|
@@ -10,8 +10,8 @@ model-index:
|
|
10 |
- name: wav2vec2-large-xls-r-300m-arabic-colab
|
11 |
results:
|
12 |
- task:
|
13 |
-
name: Automatic Speech Recognition
|
14 |
type: automatic-speech-recognition
|
|
|
15 |
dataset:
|
16 |
name: common_voice_12_0
|
17 |
type: common_voice_12_0
|
@@ -19,9 +19,9 @@ model-index:
|
|
19 |
split: test[:10%]
|
20 |
args: ar
|
21 |
metrics:
|
22 |
-
-
|
23 |
-
type: wer
|
24 |
value: 0.7661710754972002
|
|
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
+
base_model: batoula187/wav2vec2-large-xls-r-300m-arabic-colab
|
5 |
datasets:
|
6 |
- common_voice_12_0
|
7 |
metrics:
|
|
|
10 |
- name: wav2vec2-large-xls-r-300m-arabic-colab
|
11 |
results:
|
12 |
- task:
|
|
|
13 |
type: automatic-speech-recognition
|
14 |
+
name: Automatic Speech Recognition
|
15 |
dataset:
|
16 |
name: common_voice_12_0
|
17 |
type: common_voice_12_0
|
|
|
19 |
split: test[:10%]
|
20 |
args: ar
|
21 |
metrics:
|
22 |
+
- type: wer
|
|
|
23 |
value: 0.7661710754972002
|
24 |
+
name: Wer
|
25 |
---
|
26 |
|
27 |
<!-- 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>": 90,
|
3 |
+
"<s>": 89
|
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 |
+
"87": {
|
4 |
"content": "[UNK]",
|
5 |
"lstrip": true,
|
6 |
"normalized": false,
|
|
|
8 |
"single_word": false,
|
9 |
"special": false
|
10 |
},
|
11 |
+
"88": {
|
12 |
"content": "[PAD]",
|
13 |
"lstrip": true,
|
14 |
"normalized": false,
|
|
|
16 |
"single_word": false,
|
17 |
"special": false
|
18 |
},
|
19 |
+
"89": {
|
20 |
"content": "<s>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"90": {
|
28 |
"content": "</s>",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
vocab.json
CHANGED
@@ -1,68 +1,91 @@
|
|
1 |
{
|
2 |
-
"[PAD]":
|
3 |
-
"[UNK]":
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"
|
13 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
"|": 0,
|
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 |
-
"
|
51 |
-
"
|
52 |
-
"
|
53 |
-
"
|
54 |
-
"
|
55 |
-
"
|
56 |
-
"
|
57 |
-
"
|
58 |
-
"
|
59 |
-
"
|
60 |
-
"
|
61 |
-
"
|
62 |
-
"
|
63 |
-
"
|
64 |
-
"
|
65 |
-
"
|
66 |
-
"
|
67 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
68 |
}
|
|
|
1 |
{
|
2 |
+
"[PAD]": 88,
|
3 |
+
"[UNK]": 87,
|
4 |
+
"_": 1,
|
5 |
+
"a": 2,
|
6 |
+
"b": 3,
|
7 |
+
"c": 4,
|
8 |
+
"d": 5,
|
9 |
+
"e": 6,
|
10 |
+
"f": 7,
|
11 |
+
"g": 8,
|
12 |
+
"h": 9,
|
13 |
+
"i": 10,
|
14 |
+
"l": 11,
|
15 |
+
"m": 12,
|
16 |
+
"n": 13,
|
17 |
+
"o": 14,
|
18 |
+
"r": 15,
|
19 |
+
"s": 16,
|
20 |
+
"t": 17,
|
21 |
+
"u": 18,
|
22 |
+
"v": 19,
|
23 |
+
"w": 20,
|
24 |
+
"y": 21,
|
25 |
"|": 0,
|
26 |
+
"«": 22,
|
27 |
+
"»": 23,
|
28 |
+
"،": 24,
|
29 |
+
"؛": 25,
|
30 |
+
"؟": 26,
|
31 |
+
"ء": 27,
|
32 |
+
"آ": 28,
|
33 |
+
"أ": 29,
|
34 |
+
"ؤ": 30,
|
35 |
+
"إ": 31,
|
36 |
+
"ئ": 32,
|
37 |
+
"ا": 33,
|
38 |
+
"ب": 34,
|
39 |
+
"ة": 35,
|
40 |
+
"ت": 36,
|
41 |
+
"ث": 37,
|
42 |
+
"ج": 38,
|
43 |
+
"ح": 39,
|
44 |
+
"خ": 40,
|
45 |
+
"د": 41,
|
46 |
+
"ذ": 42,
|
47 |
+
"ر": 43,
|
48 |
+
"ز": 44,
|
49 |
+
"س": 45,
|
50 |
+
"ش": 46,
|
51 |
+
"ص": 47,
|
52 |
+
"ض": 48,
|
53 |
+
"ط": 49,
|
54 |
+
"ظ": 50,
|
55 |
+
"ع": 51,
|
56 |
+
"غ": 52,
|
57 |
+
"ـ": 53,
|
58 |
+
"ف": 54,
|
59 |
+
"ق": 55,
|
60 |
+
"ك": 56,
|
61 |
+
"ل": 57,
|
62 |
+
"م": 58,
|
63 |
+
"ن": 59,
|
64 |
+
"ه": 60,
|
65 |
+
"و": 61,
|
66 |
+
"ى": 62,
|
67 |
+
"ي": 63,
|
68 |
+
"ً": 64,
|
69 |
+
"ٌ": 65,
|
70 |
+
"ٍ": 66,
|
71 |
+
"َ": 67,
|
72 |
+
"ُ": 68,
|
73 |
+
"ِ": 69,
|
74 |
+
"ّ": 70,
|
75 |
+
"ْ": 71,
|
76 |
+
"ٰ": 72,
|
77 |
+
"چ": 73,
|
78 |
+
"ڨ": 74,
|
79 |
+
"ک": 75,
|
80 |
+
"ھ": 76,
|
81 |
+
"ی": 77,
|
82 |
+
"ۖ": 78,
|
83 |
+
"ۗ": 79,
|
84 |
+
"ۘ": 80,
|
85 |
+
"ۚ": 81,
|
86 |
+
"ۛ": 82,
|
87 |
+
"—": 83,
|
88 |
+
"☭": 84,
|
89 |
+
"ﺃ": 85,
|
90 |
+
"ﻻ": 86
|
91 |
}
|