Hugging Face's logo

asr-africa
/
wav2vec2-asr-africa-base-finetuned-naijavoices-hausa-v0.1

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files Community
Alvin-Nahabwe commited on
Commit
5098383
·
verified ·
1 Parent(s): 53df1e5

End of training

Browse files
Files changed (2) hide show
  1. README.md +148 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: asr-africa/wav2vec2-asr-africa-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: wav2vec2-asr-africa-base-finetuned-naijavoices-hausa-v0.1
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # wav2vec2-asr-africa-base-finetuned-naijavoices-hausa-v0.1
17
+
18
+ This model is a fine-tuned version of [asr-africa/wav2vec2-asr-africa-base](https://huggingface.co/asr-africa/wav2vec2-asr-africa-base) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.2111
21
+ - Wer: 0.2137
22
+ - Cer: 0.0544
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.0003
42
+ - train_batch_size: 128
43
+ - eval_batch_size: 64
44
+ - seed: 42
45
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 400
48
+ - num_epochs: 100.0
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
54
+ |:-------------:|:-----:|:------:|:---------------:|:------:|:------:|
55
+ | 1.2573 | 1.0 | 4339 | 0.3857 | 0.4168 | 0.1103 |
56
+ | 0.8756 | 2.0 | 8678 | 0.3528 | 0.3770 | 0.1002 |
57
+ | 0.8298 | 3.0 | 13017 | 0.3253 | 0.3464 | 0.0914 |
58
+ | 0.7952 | 4.0 | 17356 | 0.3182 | 0.3448 | 0.0922 |
59
+ | 0.7721 | 5.0 | 21695 | 0.3102 | 0.3356 | 0.0894 |
60
+ | 0.7546 | 6.0 | 26034 | 0.3009 | 0.3211 | 0.0852 |
61
+ | 0.7368 | 7.0 | 30373 | 0.2978 | 0.3209 | 0.0853 |
62
+ | 0.725 | 8.0 | 34712 | 0.2880 | 0.3160 | 0.0831 |
63
+ | 0.7114 | 9.0 | 39051 | 0.2830 | 0.3031 | 0.0801 |
64
+ | 0.7004 | 10.0 | 43390 | 0.2813 | 0.2986 | 0.0791 |
65
+ | 0.6864 | 11.0 | 47729 | 0.2744 | 0.2939 | 0.0778 |
66
+ | 0.6771 | 12.0 | 52068 | 0.2697 | 0.2888 | 0.0771 |
67
+ | 0.6713 | 13.0 | 56407 | 0.2715 | 0.2939 | 0.0773 |
68
+ | 0.6662 | 14.0 | 60746 | 0.2672 | 0.2874 | 0.0754 |
69
+ | 0.6557 | 15.0 | 65085 | 0.2664 | 0.2818 | 0.0745 |
70
+ | 0.6471 | 16.0 | 69424 | 0.2624 | 0.2847 | 0.0756 |
71
+ | 0.6368 | 17.0 | 73763 | 0.2580 | 0.2792 | 0.0729 |
72
+ | 0.6284 | 18.0 | 78102 | 0.2537 | 0.2722 | 0.0712 |
73
+ | 0.6246 | 19.0 | 82441 | 0.2531 | 0.2729 | 0.0713 |
74
+ | 0.6192 | 20.0 | 86780 | 0.2509 | 0.2761 | 0.0714 |
75
+ | 0.6121 | 21.0 | 91119 | 0.2495 | 0.2649 | 0.0694 |
76
+ | 0.605 | 22.0 | 95458 | 0.2448 | 0.2652 | 0.0693 |
77
+ | 0.6003 | 23.0 | 99797 | 0.2482 | 0.2605 | 0.0687 |
78
+ | 0.5957 | 24.0 | 104136 | 0.2435 | 0.2610 | 0.0680 |
79
+ | 0.5909 | 25.0 | 108475 | 0.2443 | 0.2637 | 0.0686 |
80
+ | 0.587 | 26.0 | 112814 | 0.2433 | 0.2645 | 0.0692 |
81
+ | 0.5815 | 27.0 | 117153 | 0.2432 | 0.2606 | 0.0680 |
82
+ | 0.5773 | 28.0 | 121492 | 0.2390 | 0.2534 | 0.0664 |
83
+ | 0.5706 | 29.0 | 125831 | 0.2373 | 0.2523 | 0.0662 |
84
+ | 0.5647 | 30.0 | 130170 | 0.2342 | 0.2566 | 0.0661 |
85
+ | 0.5601 | 31.0 | 134509 | 0.2348 | 0.2527 | 0.0655 |
86
+ | 0.5563 | 32.0 | 138848 | 0.2343 | 0.2506 | 0.0653 |
87
+ | 0.5525 | 33.0 | 143187 | 0.2332 | 0.2493 | 0.0645 |
88
+ | 0.549 | 34.0 | 147526 | 0.2345 | 0.2558 | 0.0661 |
89
+ | 0.5443 | 35.0 | 151865 | 0.2307 | 0.2439 | 0.0637 |
90
+ | 0.5423 | 36.0 | 156204 | 0.2306 | 0.2494 | 0.0641 |
91
+ | 0.5365 | 37.0 | 160543 | 0.2288 | 0.2423 | 0.0632 |
92
+ | 0.534 | 38.0 | 164882 | 0.2317 | 0.2492 | 0.0648 |
93
+ | 0.529 | 39.0 | 169221 | 0.2290 | 0.2440 | 0.0639 |
94
+ | 0.5233 | 40.0 | 173560 | 0.2255 | 0.2424 | 0.0626 |
95
+ | 0.5213 | 41.0 | 177899 | 0.2268 | 0.2477 | 0.0636 |
96
+ | 0.5157 | 42.0 | 182238 | 0.2255 | 0.2410 | 0.0622 |
97
+ | 0.512 | 43.0 | 186577 | 0.2248 | 0.2400 | 0.0622 |
98
+ | 0.508 | 44.0 | 190916 | 0.2259 | 0.2411 | 0.0623 |
99
+ | 0.5065 | 45.0 | 195255 | 0.2257 | 0.2380 | 0.0616 |
100
+ | 0.5034 | 46.0 | 199594 | 0.2224 | 0.2382 | 0.0616 |
101
+ | 0.4981 | 47.0 | 203933 | 0.2211 | 0.2353 | 0.0608 |
102
+ | 0.4954 | 48.0 | 208272 | 0.2233 | 0.2424 | 0.0627 |
103
+ | 0.4922 | 49.0 | 212611 | 0.2223 | 0.2361 | 0.0611 |
104
+ | 0.4883 | 50.0 | 216950 | 0.2188 | 0.2369 | 0.0607 |
105
+ | 0.4868 | 51.0 | 221289 | 0.2191 | 0.2309 | 0.0595 |
106
+ | 0.4811 | 52.0 | 225628 | 0.2165 | 0.2316 | 0.0593 |
107
+ | 0.4782 | 53.0 | 229967 | 0.2170 | 0.2283 | 0.0590 |
108
+ | 0.4755 | 54.0 | 234306 | 0.2204 | 0.2293 | 0.0593 |
109
+ | 0.4739 | 55.0 | 238645 | 0.2178 | 0.2333 | 0.0598 |
110
+ | 0.4707 | 56.0 | 242984 | 0.2189 | 0.2334 | 0.0598 |
111
+ | 0.4664 | 57.0 | 247323 | 0.2155 | 0.2309 | 0.0591 |
112
+ | 0.4646 | 58.0 | 251662 | 0.2166 | 0.2305 | 0.0588 |
113
+ | 0.4586 | 59.0 | 256001 | 0.2162 | 0.2257 | 0.0579 |
114
+ | 0.4575 | 60.0 | 260340 | 0.2142 | 0.2263 | 0.0580 |
115
+ | 0.4536 | 61.0 | 264679 | 0.2159 | 0.2256 | 0.0575 |
116
+ | 0.4503 | 62.0 | 269018 | 0.2146 | 0.2263 | 0.0579 |
117
+ | 0.4476 | 63.0 | 273357 | 0.2148 | 0.2259 | 0.0578 |
118
+ | 0.4456 | 64.0 | 277696 | 0.2148 | 0.2212 | 0.0567 |
119
+ | 0.4437 | 65.0 | 282035 | 0.2137 | 0.2227 | 0.0566 |
120
+ | 0.4402 | 66.0 | 286374 | 0.2122 | 0.2235 | 0.0571 |
121
+ | 0.4374 | 67.0 | 290713 | 0.2136 | 0.2199 | 0.0562 |
122
+ | 0.4343 | 68.0 | 295052 | 0.2136 | 0.2197 | 0.0565 |
123
+ | 0.431 | 69.0 | 299391 | 0.2117 | 0.2191 | 0.0561 |
124
+ | 0.4288 | 70.0 | 303730 | 0.2116 | 0.2200 | 0.0560 |
125
+ | 0.4267 | 71.0 | 308069 | 0.2153 | 0.2204 | 0.0564 |
126
+ | 0.4237 | 72.0 | 312408 | 0.2114 | 0.2200 | 0.0562 |
127
+ | 0.4208 | 73.0 | 316747 | 0.2104 | 0.2193 | 0.0558 |
128
+ | 0.419 | 74.0 | 321086 | 0.2121 | 0.2200 | 0.0561 |
129
+ | 0.4154 | 75.0 | 325425 | 0.2106 | 0.2191 | 0.0559 |
130
+ | 0.4126 | 76.0 | 329764 | 0.2121 | 0.2141 | 0.0547 |
131
+ | 0.4107 | 77.0 | 334103 | 0.2097 | 0.2190 | 0.0557 |
132
+ | 0.4078 | 78.0 | 338442 | 0.2107 | 0.2162 | 0.0551 |
133
+ | 0.406 | 79.0 | 342781 | 0.2103 | 0.2134 | 0.0544 |
134
+ | 0.4034 | 80.0 | 347120 | 0.2124 | 0.2135 | 0.0543 |
135
+ | 0.4021 | 81.0 | 351459 | 0.2095 | 0.2133 | 0.0544 |
136
+ | 0.3979 | 82.0 | 355798 | 0.2104 | 0.2146 | 0.0544 |
137
+ | 0.3977 | 83.0 | 360137 | 0.2102 | 0.2131 | 0.0544 |
138
+ | 0.3931 | 84.0 | 364476 | 0.2097 | 0.2157 | 0.0547 |
139
+ | 0.3915 | 85.0 | 368815 | 0.2116 | 0.2132 | 0.0541 |
140
+ | 0.3907 | 86.0 | 373154 | 0.2111 | 0.2137 | 0.0544 |
141
+
142
+
143
+ ### Framework versions
144
+
145
+ - Transformers 4.51.3
146
+ - Pytorch 2.6.0+cu124
147
+ - Datasets 3.5.0
148
+ - Tokenizers 0.21.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6365c122ab4578082c1b2f406862aeade87755550fba72c3985504e7c3f3039e
3
  size 377652400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d10a75ccbef747396a8b612490bc8c4c621dcbf69011d4a6545331d9ac31a068
3
  size 377652400