dpykhtar commited on
Commit
9b8d30f
1 Parent(s): 7758f02

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -15
README.md CHANGED
@@ -23,15 +23,15 @@ model-index:
23
  dataset:
24
  args:
25
  language: uk
26
- name: Mozilla Common Voice 8.0
27
  config: uk
28
  split: test
29
- type: mozilla-foundation/common_voice_8_0
30
  metrics:
31
  -
32
  name: "Test WER"
33
  type: wer
34
- value: 3.67
35
  task:
36
  name: "Automatic Speech Recognition"
37
  type: automatic-speech-recognition
@@ -39,15 +39,15 @@ model-index:
39
  dataset:
40
  args:
41
  language: uk
42
- name: Mozilla Common Voice 8.0
43
  config: uk
44
  split: dev
45
- type: mozilla-foundation/common_voice_8_0
46
  metrics:
47
  -
48
  name: "Test WER"
49
  type: wer
50
- value: 5.22
51
  task:
52
  name: "Automatic Speech Recognition"
53
  type: automatic-speech-recognition
@@ -87,15 +87,15 @@ model-index:
87
  dataset:
88
  args:
89
  language: uk
90
- name: Mozilla Common Voice 10.0
91
  config: uk
92
  split: test
93
- type: mozilla-foundation/common_voice_10_0
94
  metrics:
95
  -
96
  name: "Test WER"
97
  type: wer
98
- value: 5.04
99
  task:
100
  name: "Automatic Speech Recognition"
101
  type: automatic-speech-recognition
@@ -103,15 +103,15 @@ model-index:
103
  dataset:
104
  args:
105
  language: uk
106
- name: Mozilla Common Voice 10.0
107
  config: uk
108
  split: dev
109
- type: mozilla-foundation/common_voice_10_0
110
  metrics:
111
  -
112
  name: "Test WER"
113
  type: wer
114
- value: 4.83
115
  task:
116
  name: "Automatic Speech Recognition"
117
  type: automatic-speech-recognition
@@ -197,9 +197,9 @@ This model has been trained using validated Mozilla Common Voice Corpus 10.0 dat
197
 
198
  The list of the available models in this collection is shown in the following table. Performances of the ASR models are reported in terms of Word Error Rate (WER%) with greedy decoding.
199
 
200
- | Version | Tokenizer | Vocabulary Size | MCV-8 test | MCV-8 dev | MCV-9 test | MCV-9 dev | MCV-10 test | MCV-10 dev |
201
- | :-----------: |:---------------------:| :--------------: | :--------: | :-------: | :--------: | :-------: | :---------: | :--------: |
202
- | 1.0.0 | SentencePiece Unigram | 1024 | 3.67 | 5.22 | 3.84 | 5.09 | 5.04 | 4.83 |
203
 
204
  ## Limitations
205
 
 
23
  dataset:
24
  args:
25
  language: uk
26
+ name: Mozilla Common Voice 10.0
27
  config: uk
28
  split: test
29
+ type: mozilla-foundation/common_voice_10_0
30
  metrics:
31
  -
32
  name: "Test WER"
33
  type: wer
34
+ value: 5.04
35
  task:
36
  name: "Automatic Speech Recognition"
37
  type: automatic-speech-recognition
 
39
  dataset:
40
  args:
41
  language: uk
42
+ name: Mozilla Common Voice 10.0
43
  config: uk
44
  split: dev
45
+ type: mozilla-foundation/common_voice_10_0
46
  metrics:
47
  -
48
  name: "Test WER"
49
  type: wer
50
+ value: 4.83
51
  task:
52
  name: "Automatic Speech Recognition"
53
  type: automatic-speech-recognition
 
87
  dataset:
88
  args:
89
  language: uk
90
+ name: Mozilla Common Voice 8.0
91
  config: uk
92
  split: test
93
+ type: mozilla-foundation/common_voice_8_0
94
  metrics:
95
  -
96
  name: "Test WER"
97
  type: wer
98
+ value: 3.67
99
  task:
100
  name: "Automatic Speech Recognition"
101
  type: automatic-speech-recognition
 
103
  dataset:
104
  args:
105
  language: uk
106
+ name: Mozilla Common Voice 8.0
107
  config: uk
108
  split: dev
109
+ type: mozilla-foundation/common_voice_8_0
110
  metrics:
111
  -
112
  name: "Test WER"
113
  type: wer
114
+ value: 5.22
115
  task:
116
  name: "Automatic Speech Recognition"
117
  type: automatic-speech-recognition
 
197
 
198
  The list of the available models in this collection is shown in the following table. Performances of the ASR models are reported in terms of Word Error Rate (WER%) with greedy decoding.
199
 
200
+ | Version | Tokenizer | Vocabulary Size | MCV-10 test | MCV-10 dev | MCV-9 test | MCV-9 dev | MCV-8 test | MCV-8 dev |
201
+ | :-----------: |:---------------------:| :--------------: | :---------: | :--------: | :--------: | :-------: | :--------: | :-------: |
202
+ | 1.0.0 | SentencePiece Unigram | 1024 | 5.04 | 4.83 | 3.84 | 5.09 | 3.67 | 5.22 |
203
 
204
  ## Limitations
205