Hugging Face's logo

BSC-LT
/
ConMamba-small-ca

Automatic Speech Recognition
Catalan
audio
catalan
mamba-models
catalonia
barcelona-supercomputing-center
Eval Results (legacy)
Model card Files
xet
 Community
AbirMessaoudi commited on
Commit
5246a9f
·
verified ·
1 Parent(s): d2fef06

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +183 -0
README.md CHANGED
@@ -9,6 +9,189 @@ tags:
9
  - mamba-models
10
  - catalonia
11
  - barcelona-supercomputing-center
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  ---
13
  # ConMamba-small-ca-
14
 
 
9
  - mamba-models
10
  - catalonia
11
  - barcelona-supercomputing-center
12
+ model-index:
13
+ - name: ConMamba-small-ca
14
+ results:
15
+ - task:
16
+ type: automatic-speech-recognition
17
+ name: Automatic Speech Recognition
18
+ dataset:
19
+ name: 3cat-parla-asr
20
+ type: "projecte-aina/3catparla_asr"
21
+ config: ca
22
+ split: test
23
+ metrics:
24
+ - type: wer
25
+ value: 2.81
26
+ name: Test WER
27
+ - task:
28
+ type: automatic-speech-recognition
29
+ name: Automatic Speech Recognition
30
+ dataset:
31
+ name: parla_clean
32
+ type: "projecte-aina/parlament_parla_v3"
33
+ config: ca
34
+ split: test
35
+ metrics:
36
+ - type: wer
37
+ value: 5.47
38
+ name: Test WER
39
+ - task:
40
+ type: automatic-speech-recognition
41
+ name: Automatic Speech Recognition
42
+ dataset:
43
+ name: parla_other
44
+ type: "projecte-aina/parlament_parla_v3"
45
+ config: ca
46
+ split: test
47
+ metrics:
48
+ - type: wer
49
+ value: 12.05
50
+ name: Test WER
51
+ - task:
52
+ type: automatic-speech-recognition
53
+ name: Automatic Speech Recognition
54
+ dataset:
55
+ name: corts_clean_anon
56
+ type: "projecte-aina/corts_valencianes_asr_a"
57
+ config: ca
58
+ split: test
59
+ metrics:
60
+ - type: wer
61
+ value: 20.09
62
+ name: Test WER
63
+ - task:
64
+ type: automatic-speech-recognition
65
+ name: Automatic Speech Recognition
66
+ dataset:
67
+ name: corts_other_anon
68
+ type: "projecte-aina/corts_valencianes_asr_a"
69
+ config: ca
70
+ split: test
71
+ metrics:
72
+ - type: wer
73
+ value: 36.91
74
+ name: Test WER
75
+ - task:
76
+ type: automatic-speech-recognition
77
+ name: Automatic Speech Recognition
78
+ dataset:
79
+ name: central_male
80
+ type: "projecte-aina/annotated_catalan_common_voice_v17"
81
+ config: ca
82
+ split: test
83
+ metrics:
84
+ - type: wer
85
+ value: 7.73
86
+ name: Test WER
87
+ - task:
88
+ type: automatic-speech-recognition
89
+ name: Automatic Speech Recognition
90
+ dataset:
91
+ name: central_female
92
+ type: "projecte-aina/annotated_catalan_common_voice_v17"
93
+ config: ca
94
+ split: test
95
+ metrics:
96
+ - type: wer
97
+ value: 6.84
98
+ name: Test WER
99
+ - task:
100
+ type: automatic-speech-recognition
101
+ name: Automatic Speech Recognition
102
+ dataset:
103
+ name: valencia_male
104
+ type: "projecte-aina/annotated_catalan_common_voice_v17"
105
+ config: ca
106
+ split: test
107
+ metrics:
108
+ - type: wer
109
+ value: 8.30
110
+ name: Test WER
111
+ - task:
112
+ type: automatic-speech-recognition
113
+ name: Automatic Speech Recognition
114
+ dataset:
115
+ name: valencia_female
116
+ type: "projecte-aina/annotated_catalan_common_voice_v17"
117
+ config: ca
118
+ split: test
119
+ metrics:
120
+ - type: wer
121
+ value: 7.32
122
+ name: Test WER
123
+ - task:
124
+ type: automatic-speech-recognition
125
+ name: Automatic Speech Recognition
126
+ dataset:
127
+ name: balearic_male
128
+ type: "projecte-aina/annotated_catalan_common_voice_v17"
129
+ config: ca
130
+ split: test
131
+ metrics:
132
+ - type: wer
133
+ value: 8.78
134
+ name: Test WER
135
+ - task:
136
+ type: automatic-speech-recognition
137
+ name: Automatic Speech Recognition
138
+ dataset:
139
+ name: balearic_female
140
+ type: "projecte-aina/annotated_catalan_common_voice_v17"
141
+ config: ca
142
+ split: test
143
+ metrics:
144
+ - type: wer
145
+ value: 9.57
146
+ name: Test WER
147
+ - task:
148
+ type: automatic-speech-recognition
149
+ name: Automatic Speech Recognition
150
+ dataset:
151
+ name: northern_male
152
+ type: "projecte-aina/annotated_catalan_common_voice_v17"
153
+ config: ca
154
+ split: test
155
+ metrics:
156
+ - type: wer
157
+ value: 7.38
158
+ name: Test WER
159
+ - task:
160
+ type: automatic-speech-recognition
161
+ name: Automatic Speech Recognition
162
+ dataset:
163
+ name: northern_female
164
+ type: "projecte-aina/annotated_catalan_common_voice_v17"
165
+ config: ca
166
+ split: test
167
+ metrics:
168
+ - type: wer
169
+ value: 6.45
170
+ name: Test WER
171
+ - task:
172
+ type: automatic-speech-recognition
173
+ name: Automatic Speech Recognition
174
+ dataset:
175
+ name: northwestern_male
176
+ type: "projecte-aina/annotated_catalan_common_voice_v17"
177
+ config: ca
178
+ split: test
179
+ metrics:
180
+ - type: wer
181
+ value: 7.84
182
+ name: Test WER
183
+ - task:
184
+ type: automatic-speech-recognition
185
+ name: Automatic Speech Recognition
186
+ dataset:
187
+ name: northwestern_female
188
+ type: "projecte-aina/annotated_catalan_common_voice_v17"
189
+ config: ca
190
+ split: test
191
+ metrics:
192
+ - type: wer
193
+ value: 6.05
194
+ name: Test WER
195
  ---
196
  # ConMamba-small-ca-
197