Hugging Face's logo

badili
/
metaasr-1-b-mcv-11-v-1

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
3
lyimo commited on
Commit
8c1be54
•
1 Parent(s): 5171887

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +163 -0
README.md ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice_11_0
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: wav2vec2-large-xls-r-1b-swahili-v12
11
+ results:
12
+ - task:
13
+ name: Automatic Speech Recognition
14
+ type: automatic-speech-recognition
15
+ dataset:
16
+ name: common_voice_11_0
17
+ type: common_voice_11_0
18
+ config: sw
19
+ split: test
20
+ args: sw
21
+ metrics:
22
+ - name: Wer
23
+ type: wer
24
+ value: 0.20382121671954753
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # wav2vec2-large-xls-r-1b-swahili-v12
31
+
32
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the common_voice_11_0 dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.4658
35
+ - Wer: 0.2038
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 0.0003
55
+ - train_batch_size: 16
56
+ - eval_batch_size: 8
57
+ - seed: 42
58
+ - gradient_accumulation_steps: 2
59
+ - total_train_batch_size: 32
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_steps: 500
63
+ - num_epochs: 30
64
+ - mixed_precision_training: Native AMP
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
69
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
70
+ | 2.726 | 0.35 | 400 | 0.7214 | 0.6674 |
71
+ | 0.5241 | 0.69 | 800 | 0.5641 | 0.5345 |
72
+ | 0.4616 | 1.04 | 1200 | 0.5112 | 0.4755 |
73
+ | 0.4018 | 1.39 | 1600 | 0.4797 | 0.4158 |
74
+ | 0.3916 | 1.74 | 2000 | 0.4483 | 0.3985 |
75
+ | 0.3661 | 2.08 | 2400 | 0.4449 | 0.3931 |
76
+ | 0.3314 | 2.43 | 2800 | 0.4124 | 0.3549 |
77
+ | 0.3287 | 2.78 | 3200 | 0.4008 | 0.3651 |
78
+ | 0.317 | 3.13 | 3600 | 0.4460 | 0.3735 |
79
+ | 0.3026 | 3.47 | 4000 | 0.4165 | 0.3753 |
80
+ | 0.3061 | 3.82 | 4400 | 0.4112 | 0.3550 |
81
+ | 0.2808 | 4.17 | 4800 | 0.3951 | 0.3275 |
82
+ | 0.2641 | 4.52 | 5200 | 0.3934 | 0.3340 |
83
+ | 0.2709 | 4.86 | 5600 | 0.3963 | 0.3287 |
84
+ | 0.2586 | 5.21 | 6000 | 0.4114 | 0.3396 |
85
+ | 0.2487 | 5.56 | 6400 | 0.3821 | 0.3214 |
86
+ | 0.2618 | 5.91 | 6800 | 0.3987 | 0.3268 |
87
+ | 0.2297 | 6.25 | 7200 | 0.3810 | 0.3132 |
88
+ | 0.2337 | 6.6 | 7600 | 0.3740 | 0.3131 |
89
+ | 0.2285 | 6.95 | 8000 | 0.3715 | 0.3093 |
90
+ | 0.2173 | 7.29 | 8400 | 0.3878 | 0.3147 |
91
+ | 0.2251 | 7.64 | 8800 | 0.3862 | 0.3134 |
92
+ | 0.2215 | 7.99 | 9200 | 0.3621 | 0.2940 |
93
+ | 0.195 | 8.34 | 9600 | 0.3651 | 0.3005 |
94
+ | 0.201 | 8.68 | 10000 | 0.3837 | 0.3167 |
95
+ | 0.1964 | 9.03 | 10400 | 0.3719 | 0.2876 |
96
+ | 0.1741 | 9.38 | 10800 | 0.3637 | 0.2840 |
97
+ | 0.181 | 9.73 | 11200 | 0.3616 | 0.2914 |
98
+ | 0.1795 | 10.07 | 11600 | 0.3719 | 0.2753 |
99
+ | 0.1602 | 10.42 | 12000 | 0.3618 | 0.2856 |
100
+ | 0.1753 | 10.77 | 12400 | 0.3570 | 0.2788 |
101
+ | 0.1627 | 11.12 | 12800 | 0.3500 | 0.2719 |
102
+ | 0.1566 | 11.46 | 13200 | 0.3553 | 0.2808 |
103
+ | 0.1589 | 11.81 | 13600 | 0.3635 | 0.2699 |
104
+ | 0.1511 | 12.16 | 14000 | 0.3656 | 0.2692 |
105
+ | 0.1451 | 12.51 | 14400 | 0.3759 | 0.2759 |
106
+ | 0.1444 | 12.85 | 14800 | 0.3607 | 0.2677 |
107
+ | 0.1359 | 13.2 | 15200 | 0.3852 | 0.2660 |
108
+ | 0.1313 | 13.55 | 15600 | 0.3587 | 0.2679 |
109
+ | 0.1329 | 13.89 | 16000 | 0.3548 | 0.2584 |
110
+ | 0.1163 | 14.24 | 16400 | 0.3701 | 0.2535 |
111
+ | 0.1175 | 14.59 | 16800 | 0.3693 | 0.2638 |
112
+ | 0.1242 | 14.94 | 17200 | 0.3660 | 0.2565 |
113
+ | 0.1067 | 15.28 | 17600 | 0.3835 | 0.2581 |
114
+ | 0.1077 | 15.63 | 18000 | 0.3799 | 0.2504 |
115
+ | 0.1099 | 15.98 | 18400 | 0.3598 | 0.2478 |
116
+ | 0.0952 | 16.33 | 18800 | 0.3865 | 0.2563 |
117
+ | 0.1007 | 16.67 | 19200 | 0.3630 | 0.2565 |
118
+ | 0.0999 | 17.02 | 19600 | 0.3912 | 0.2505 |
119
+ | 0.0895 | 17.37 | 20000 | 0.3934 | 0.2631 |
120
+ | 0.0974 | 17.72 | 20400 | 0.3718 | 0.2462 |
121
+ | 0.0939 | 18.06 | 20800 | 0.4001 | 0.2587 |
122
+ | 0.0915 | 18.41 | 21200 | 0.4048 | 0.2468 |
123
+ | 0.0865 | 18.76 | 21600 | 0.3860 | 0.2415 |
124
+ | 0.0784 | 19.11 | 22000 | 0.4148 | 0.2454 |
125
+ | 0.0782 | 19.45 | 22400 | 0.3952 | 0.2471 |
126
+ | 0.0775 | 19.8 | 22800 | 0.3943 | 0.2434 |
127
+ | 0.0735 | 20.15 | 23200 | 0.4093 | 0.2405 |
128
+ | 0.0679 | 20.5 | 23600 | 0.3996 | 0.2362 |
129
+ | 0.0677 | 20.84 | 24000 | 0.4133 | 0.2365 |
130
+ | 0.0687 | 21.19 | 24400 | 0.4303 | 0.2330 |
131
+ | 0.0651 | 21.54 | 24800 | 0.4288 | 0.2326 |
132
+ | 0.0647 | 21.88 | 25200 | 0.4134 | 0.2347 |
133
+ | 0.0634 | 22.23 | 25600 | 0.4148 | 0.2312 |
134
+ | 0.0592 | 22.58 | 26000 | 0.4322 | 0.2315 |
135
+ | 0.06 | 22.93 | 26400 | 0.4050 | 0.2313 |
136
+ | 0.0561 | 23.27 | 26800 | 0.4260 | 0.2263 |
137
+ | 0.0546 | 23.62 | 27200 | 0.4228 | 0.2238 |
138
+ | 0.0548 | 23.97 | 27600 | 0.4140 | 0.2258 |
139
+ | 0.0505 | 24.32 | 28000 | 0.4304 | 0.2246 |
140
+ | 0.0501 | 24.66 | 28400 | 0.4241 | 0.2233 |
141
+ | 0.0481 | 25.01 | 28800 | 0.4385 | 0.2209 |
142
+ | 0.0469 | 25.36 | 29200 | 0.4451 | 0.2189 |
143
+ | 0.0464 | 25.71 | 29600 | 0.4397 | 0.2217 |
144
+ | 0.0438 | 26.05 | 30000 | 0.4419 | 0.2154 |
145
+ | 0.0432 | 26.4 | 30400 | 0.4366 | 0.2137 |
146
+ | 0.0419 | 26.75 | 30800 | 0.4371 | 0.2137 |
147
+ | 0.0419 | 27.1 | 31200 | 0.4552 | 0.2109 |
148
+ | 0.0392 | 27.44 | 31600 | 0.4496 | 0.2108 |
149
+ | 0.0386 | 27.79 | 32000 | 0.4585 | 0.2096 |
150
+ | 0.0387 | 28.14 | 32400 | 0.4496 | 0.2065 |
151
+ | 0.0367 | 28.48 | 32800 | 0.4646 | 0.2082 |
152
+ | 0.0357 | 28.83 | 33200 | 0.4553 | 0.2067 |
153
+ | 0.0355 | 29.18 | 33600 | 0.4615 | 0.2055 |
154
+ | 0.0345 | 29.53 | 34000 | 0.4670 | 0.2046 |
155
+ | 0.0346 | 29.87 | 34400 | 0.4658 | 0.2038 |
156
+
157
+
158
+ ### Framework versions
159
+
160
+ - Transformers 4.29.0.dev0
161
+ - Pytorch 2.0.0+cu117
162
+ - Datasets 2.12.0
163
+ - Tokenizers 0.13.3