cahya commited on
Commit
61d1c08
1 Parent(s): ca2e65f

updated README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -32
README.md CHANGED
@@ -13,20 +13,6 @@ datasets:
13
  model-index:
14
  - name: Wav2Vec2 Base Turkish by Cahya
15
  results:
16
- - task:
17
- name: Automatic Speech Recognition
18
- type: automatic-speech-recognition
19
- dataset:
20
- name: Common Voice 6.1
21
- type: common_voice
22
- args: tr
23
- metrics:
24
- - name: Test WER
25
- type: wer
26
- value: 9.437
27
- - name: Test CER
28
- type: cer
29
- value: 3.325
30
  - task:
31
  name: Automatic Speech Recognition
32
  type: automatic-speech-recognition
@@ -41,20 +27,6 @@ model-index:
41
  - name: Test CER
42
  type: cer
43
  value: 2.802
44
- - task:
45
- name: Automatic Speech Recognition
46
- type: automatic-speech-recognition
47
- dataset:
48
- name: Common Voice 8
49
- type: mozilla-foundation/common_voice_8_0
50
- args: tr
51
- metrics:
52
- - name: Test WER
53
- type: wer
54
- value: 8.335
55
- - name: Test CER
56
- type: cer
57
- value: 2.336
58
  - task:
59
  name: Automatic Speech Recognition
60
  type: automatic-speech-recognition
@@ -70,10 +42,7 @@ model-index:
70
  type: cer
71
  value: 10.66
72
  ---
73
-
74
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
75
- should probably proofread and complete it, then remove this comment. -->
76
-
77
  #
78
 
79
  This model is a fine-tuned version of [cahya/wav2vec2-base-turkish-artificial-cv](https://huggingface.co/cahya/wav2vec2-base-turkish-artificial-cv) on the COMMON_VOICE - TR dataset.
@@ -81,6 +50,14 @@ It achieves the following results on the evaluation set:
81
  - Loss: 0.1337
82
  - Wer: 0.1353
83
 
 
 
 
 
 
 
 
 
84
  ## Model description
85
 
86
  More information needed
 
13
  model-index:
14
  - name: Wav2Vec2 Base Turkish by Cahya
15
  results:
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
  - task:
17
  name: Automatic Speech Recognition
18
  type: automatic-speech-recognition
 
27
  - name: Test CER
28
  type: cer
29
  value: 2.802
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  - task:
31
  name: Automatic Speech Recognition
32
  type: automatic-speech-recognition
 
42
  type: cer
43
  value: 10.66
44
  ---
45
+
 
 
 
46
  #
47
 
48
  This model is a fine-tuned version of [cahya/wav2vec2-base-turkish-artificial-cv](https://huggingface.co/cahya/wav2vec2-base-turkish-artificial-cv) on the COMMON_VOICE - TR dataset.
 
50
  - Loss: 0.1337
51
  - Wer: 0.1353
52
 
53
+
54
+ | | Dataset | WER | CER |
55
+ |---|-------------------------------|---------|----------|
56
+ | 1 | Common Voice 6.1 | 9.437 | 3.325 |
57
+ | 2 | Common Voice 7.0 | 8.147 | 2.802 |
58
+ | 3 | Common Voice 8.0 | 8.335 | 2.336 |
59
+ | 4 | Speech Recognition Community | 28.011 | 10.66 |
60
+
61
  ## Model description
62
 
63
  More information needed