Hugging Face's logo

dmusingu
/
muk-luganda-digits-classification

Audio Classification
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
Community
dmusingu commited on
Commit
dc188bf
·
verified ·
1 Parent(s): 7dc6964

End of training

Browse files
Files changed (4) hide show
  1. README.md +43 -63
  2. config.json +3 -1
  3. model.safetensors +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 4.3197
22
- - Accuracy: 0.4
23
 
24
  ## Model description
25
 
@@ -45,72 +45,52 @@ The following hyperparameters were used during training:
45
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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_ratio: 0.1
48
- - num_epochs: 60
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
- | 2.3032 | 1.0 | 60 | 2.2913 | 0.1667 |
55
- | 2.3008 | 2.0 | 120 | 2.2853 | 0.1333 |
56
- | 2.2908 | 3.0 | 180 | 2.2906 | 0.1 |
57
- | 2.2746 | 4.0 | 240 | 2.2676 | 0.2333 |
58
- | 2.227 | 5.0 | 300 | 2.2602 | 0.1333 |
59
- | 2.1679 | 6.0 | 360 | 2.2250 | 0.1333 |
60
- | 2.0793 | 7.0 | 420 | 2.1667 | 0.3 |
61
- | 1.9567 | 8.0 | 480 | 2.3147 | 0.1333 |
62
- | 1.8217 | 9.0 | 540 | 2.0799 | 0.3 |
63
- | 1.6949 | 10.0 | 600 | 2.1671 | 0.2 |
64
- | 1.677 | 11.0 | 660 | 2.1748 | 0.2667 |
65
- | 1.5748 | 12.0 | 720 | 2.1790 | 0.2 |
66
- | 1.4176 | 13.0 | 780 | 2.1468 | 0.2333 |
67
- | 1.2679 | 14.0 | 840 | 2.1294 | 0.3 |
68
- | 1.2619 | 15.0 | 900 | 1.9716 | 0.3667 |
69
- | 1.0977 | 16.0 | 960 | 2.0866 | 0.3 |
70
- | 1.0127 | 17.0 | 1020 | 2.0008 | 0.3333 |
71
- | 0.9106 | 18.0 | 1080 | 2.1988 | 0.3667 |
72
- | 0.8672 | 19.0 | 1140 | 1.9639 | 0.4 |
73
- | 0.7688 | 20.0 | 1200 | 2.1911 | 0.3 |
74
- | 0.6587 | 21.0 | 1260 | 2.2897 | 0.4 |
75
- | 0.5866 | 22.0 | 1320 | 2.5786 | 0.3333 |
76
- | 0.5267 | 23.0 | 1380 | 2.4252 | 0.3667 |
77
- | 0.5111 | 24.0 | 1440 | 2.6801 | 0.3667 |
78
- | 0.4246 | 25.0 | 1500 | 2.9816 | 0.3333 |
79
- | 0.476 | 26.0 | 1560 | 3.2478 | 0.3 |
80
- | 0.4169 | 27.0 | 1620 | 3.3604 | 0.3333 |
81
- | 0.3443 | 28.0 | 1680 | 3.5810 | 0.3333 |
82
- | 0.3004 | 29.0 | 1740 | 3.2561 | 0.4 |
83
- | 0.2123 | 30.0 | 1800 | 2.9655 | 0.5 |
84
- | 0.2302 | 31.0 | 1860 | 3.5154 | 0.4 |
85
- | 0.3316 | 32.0 | 1920 | 3.6515 | 0.3667 |
86
- | 0.1991 | 33.0 | 1980 | 3.5827 | 0.4333 |
87
- | 0.236 | 34.0 | 2040 | 3.5531 | 0.4 |
88
- | 0.2409 | 35.0 | 2100 | 3.4890 | 0.4333 |
89
- | 0.2284 | 36.0 | 2160 | 3.6660 | 0.4667 |
90
- | 0.2485 | 37.0 | 2220 | 4.2194 | 0.3667 |
91
- | 0.2069 | 38.0 | 2280 | 4.2314 | 0.3667 |
92
- | 0.2054 | 39.0 | 2340 | 4.0748 | 0.4 |
93
- | 0.1547 | 40.0 | 2400 | 4.1912 | 0.3667 |
94
- | 0.2477 | 41.0 | 2460 | 4.5107 | 0.3 |
95
- | 0.1631 | 42.0 | 2520 | 4.4653 | 0.3 |
96
- | 0.1864 | 43.0 | 2580 | 4.4574 | 0.3333 |
97
- | 0.1747 | 44.0 | 2640 | 4.4162 | 0.4 |
98
- | 0.168 | 45.0 | 2700 | 4.4537 | 0.3333 |
99
- | 0.1869 | 46.0 | 2760 | 4.1755 | 0.4 |
100
- | 0.149 | 47.0 | 2820 | 4.3228 | 0.3667 |
101
- | 0.2153 | 48.0 | 2880 | 4.6288 | 0.3667 |
102
- | 0.2022 | 49.0 | 2940 | 4.3906 | 0.3667 |
103
- | 0.1711 | 50.0 | 3000 | 4.4324 | 0.3333 |
104
- | 0.1527 | 51.0 | 3060 | 4.3020 | 0.3667 |
105
- | 0.1597 | 52.0 | 3120 | 4.4839 | 0.3667 |
106
- | 0.1717 | 53.0 | 3180 | 4.6492 | 0.3333 |
107
- | 0.2392 | 54.0 | 3240 | 4.6018 | 0.3667 |
108
- | 0.1743 | 55.0 | 3300 | 4.4345 | 0.3667 |
109
- | 0.1432 | 56.0 | 3360 | 4.3939 | 0.3667 |
110
- | 0.1834 | 57.0 | 3420 | 4.3642 | 0.4 |
111
- | 0.1457 | 58.0 | 3480 | 4.3267 | 0.4 |
112
- | 0.1335 | 59.0 | 3540 | 4.3221 | 0.4 |
113
- | 0.1305 | 60.0 | 3600 | 4.3197 | 0.4 |
114
 
115
 
116
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 3.1383
22
+ - Accuracy: 0.4118
23
 
24
  ## Model description
25
 
 
45
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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_ratio: 0.1
48
+ - num_epochs: 40
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | 2.3979 | 1.0 | 68 | 2.3931 | 0.1176 |
55
+ | 2.3557 | 2.0 | 136 | 2.3405 | 0.1765 |
56
+ | 2.2886 | 3.0 | 204 | 2.3076 | 0.2353 |
57
+ | 2.2136 | 4.0 | 272 | 2.2603 | 0.1471 |
58
+ | 2.1519 | 5.0 | 340 | 2.2511 | 0.2059 |
59
+ | 2.0177 | 6.0 | 408 | 2.1587 | 0.2353 |
60
+ | 1.9045 | 7.0 | 476 | 2.2249 | 0.3529 |
61
+ | 1.763 | 8.0 | 544 | 2.2783 | 0.2647 |
62
+ | 1.6427 | 9.0 | 612 | 2.0562 | 0.3824 |
63
+ | 1.5392 | 10.0 | 680 | 2.0552 | 0.3529 |
64
+ | 1.3602 | 11.0 | 748 | 1.9803 | 0.3529 |
65
+ | 1.3406 | 12.0 | 816 | 1.9426 | 0.4412 |
66
+ | 1.2032 | 13.0 | 884 | 2.0370 | 0.3529 |
67
+ | 1.0842 | 14.0 | 952 | 1.9971 | 0.5 |
68
+ | 1.0615 | 15.0 | 1020 | 1.8678 | 0.4412 |
69
+ | 0.9674 | 16.0 | 1088 | 1.8230 | 0.4706 |
70
+ | 0.808 | 17.0 | 1156 | 1.9590 | 0.4412 |
71
+ | 0.7434 | 18.0 | 1224 | 2.0104 | 0.4412 |
72
+ | 0.6936 | 19.0 | 1292 | 2.1243 | 0.4118 |
73
+ | 0.5685 | 20.0 | 1360 | 1.9530 | 0.4706 |
74
+ | 0.5631 | 21.0 | 1428 | 2.0039 | 0.4118 |
75
+ | 0.4919 | 22.0 | 1496 | 2.3431 | 0.4118 |
76
+ | 0.4903 | 23.0 | 1564 | 2.5384 | 0.4412 |
77
+ | 0.4504 | 24.0 | 1632 | 2.3131 | 0.4412 |
78
+ | 0.361 | 25.0 | 1700 | 2.6200 | 0.3824 |
79
+ | 0.3683 | 26.0 | 1768 | 2.6182 | 0.4118 |
80
+ | 0.3205 | 27.0 | 1836 | 2.5689 | 0.4412 |
81
+ | 0.2389 | 28.0 | 1904 | 2.6241 | 0.4706 |
82
+ | 0.1786 | 29.0 | 1972 | 2.7555 | 0.4412 |
83
+ | 0.1627 | 30.0 | 2040 | 2.6370 | 0.5 |
84
+ | 0.1764 | 31.0 | 2108 | 3.3250 | 0.3529 |
85
+ | 0.2364 | 32.0 | 2176 | 2.9069 | 0.4412 |
86
+ | 0.1772 | 33.0 | 2244 | 2.9289 | 0.4118 |
87
+ | 0.1929 | 34.0 | 2312 | 3.1186 | 0.4118 |
88
+ | 0.2075 | 35.0 | 2380 | 3.1905 | 0.4118 |
89
+ | 0.1517 | 36.0 | 2448 | 3.0900 | 0.4118 |
90
+ | 0.149 | 37.0 | 2516 | 3.1103 | 0.3824 |
91
+ | 0.1156 | 38.0 | 2584 | 3.1738 | 0.4412 |
92
+ | 0.2291 | 39.0 | 2652 | 3.1478 | 0.4412 |
93
+ | 0.1768 | 40.0 | 2720 | 3.1383 | 0.4118 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
94
 
95
 
96
  ### Framework versions
config.json CHANGED
@@ -66,7 +66,8 @@
66
  "6": "mukaaga",
67
  "7": "musanvu",
68
  "8": "munaana",
69
- "9": "mwenda"
 
70
  },
71
  "initializer_range": 0.02,
72
  "intermediate_size": 3072,
@@ -78,6 +79,7 @@
78
  "musanvu": 7,
79
  "mwenda": 9,
80
  "nnya": 4,
 
81
  "notti": 0,
82
  "ssatu": 3,
83
  "ttaano": 5
 
66
  "6": "mukaaga",
67
  "7": "musanvu",
68
  "8": "munaana",
69
+ "9": "mwenda",
70
+ "10": "noise"
71
  },
72
  "initializer_range": 0.02,
73
  "intermediate_size": 3072,
 
79
  "musanvu": 7,
80
  "mwenda": 9,
81
  "nnya": 4,
82
+ "noise": 10,
83
  "notti": 0,
84
  "ssatu": 3,
85
  "ttaano": 5
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5b720826f075746b0f706357f9f0e55fe6e230a00f5bd524a4b27669a6a17dc
3
- size 378310592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4581d7d25cafd2fc0ca659443bdf37b40a26f61c22f7b450e8fafd2034f2dd09
3
+ size 378311620
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03c823224345b9c5433a1475603bcb47aa42baa99cc4bb00099e6a988d31dbd7
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eac59fad003ccf0373355ffe0721cdbd463969fb18e63ed41d4f8743cf91825
3
  size 5905