Mengkedalai
commited on
Commit
•
c048d0a
1
Parent(s):
2566948
Upload tokenizer
Browse files- README.md +6 -6
- vocab.json +38 -38
README.md
CHANGED
@@ -1,18 +1,18 @@
|
|
1 |
---
|
2 |
-
license: apache-2.0
|
3 |
base_model: facebook/wav2vec2-large-xlsr-53
|
4 |
-
tags:
|
5 |
-
- generated_from_trainer
|
6 |
datasets:
|
7 |
- common_voice_17_0
|
|
|
8 |
metrics:
|
9 |
- wer
|
|
|
|
|
10 |
model-index:
|
11 |
- name: wav2vec2-large-xlsr-Mongolian-cv17-base
|
12 |
results:
|
13 |
- task:
|
14 |
-
name: Automatic Speech Recognition
|
15 |
type: automatic-speech-recognition
|
|
|
16 |
dataset:
|
17 |
name: common_voice_17_0
|
18 |
type: common_voice_17_0
|
@@ -20,9 +20,9 @@ model-index:
|
|
20 |
split: validation
|
21 |
args: mn
|
22 |
metrics:
|
23 |
-
-
|
24 |
-
type: wer
|
25 |
value: 1.0
|
|
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
1 |
---
|
|
|
2 |
base_model: facebook/wav2vec2-large-xlsr-53
|
|
|
|
|
3 |
datasets:
|
4 |
- common_voice_17_0
|
5 |
+
license: apache-2.0
|
6 |
metrics:
|
7 |
- wer
|
8 |
+
tags:
|
9 |
+
- generated_from_trainer
|
10 |
model-index:
|
11 |
- name: wav2vec2-large-xlsr-Mongolian-cv17-base
|
12 |
results:
|
13 |
- task:
|
|
|
14 |
type: automatic-speech-recognition
|
15 |
+
name: Automatic Speech Recognition
|
16 |
dataset:
|
17 |
name: common_voice_17_0
|
18 |
type: common_voice_17_0
|
|
|
20 |
split: validation
|
21 |
args: mn
|
22 |
metrics:
|
23 |
+
- type: wer
|
|
|
24 |
value: 1.0
|
25 |
+
name: Wer
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
vocab.json
CHANGED
@@ -1,43 +1,43 @@
|
|
1 |
{
|
2 |
-
"'":
|
3 |
"[PAD]": 40,
|
4 |
"[UNK]": 39,
|
5 |
-
"h":
|
6 |
-
"|":
|
7 |
-
"«":
|
8 |
-
"»":
|
9 |
-
"а":
|
10 |
-
"б":
|
11 |
-
"в":
|
12 |
-
"г":
|
13 |
-
"д":
|
14 |
-
"е":
|
15 |
-
"ж":
|
16 |
-
"з":
|
17 |
-
"и":
|
18 |
-
"й":
|
19 |
-
"к":
|
20 |
-
"л":
|
21 |
-
"м":
|
22 |
-
"н":
|
23 |
-
"о":
|
24 |
-
"п":
|
25 |
-
"р":
|
26 |
-
"с":
|
27 |
-
"т":
|
28 |
-
"у":
|
29 |
-
"ф":
|
30 |
-
"х":
|
31 |
-
"ц":
|
32 |
-
"ч":
|
33 |
-
"ш":
|
34 |
-
"ъ":
|
35 |
-
"ы":
|
36 |
-
"ь":
|
37 |
-
"э":
|
38 |
-
"ю":
|
39 |
-
"я":
|
40 |
"ё": 10,
|
41 |
-
"ү":
|
42 |
-
"ө":
|
43 |
}
|
|
|
1 |
{
|
2 |
+
"'": 28,
|
3 |
"[PAD]": 40,
|
4 |
"[UNK]": 39,
|
5 |
+
"h": 18,
|
6 |
+
"|": 9,
|
7 |
+
"«": 4,
|
8 |
+
"»": 6,
|
9 |
+
"а": 34,
|
10 |
+
"б": 35,
|
11 |
+
"в": 12,
|
12 |
+
"г": 30,
|
13 |
+
"д": 27,
|
14 |
+
"е": 36,
|
15 |
+
"ж": 24,
|
16 |
+
"з": 15,
|
17 |
+
"и": 1,
|
18 |
+
"й": 20,
|
19 |
+
"к": 17,
|
20 |
+
"л": 3,
|
21 |
+
"м": 11,
|
22 |
+
"н": 2,
|
23 |
+
"о": 13,
|
24 |
+
"п": 14,
|
25 |
+
"р": 21,
|
26 |
+
"с": 22,
|
27 |
+
"т": 29,
|
28 |
+
"у": 0,
|
29 |
+
"ф": 38,
|
30 |
+
"х": 16,
|
31 |
+
"ц": 19,
|
32 |
+
"ч": 8,
|
33 |
+
"ш": 37,
|
34 |
+
"ъ": 5,
|
35 |
+
"ы": 33,
|
36 |
+
"ь": 25,
|
37 |
+
"э": 7,
|
38 |
+
"ю": 31,
|
39 |
+
"я": 26,
|
40 |
"ё": 10,
|
41 |
+
"ү": 32,
|
42 |
+
"ө": 23
|
43 |
}
|