Hugging Face's logo

tuanio
/
w2v2_ablation_with_ling_head-0drop-load-best-per-best_on_tp0.025_tl10_fp0.001_fl16

Transformers
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
tuanio commited on
Commit
f7f73eb
·
1 Parent(s): 6d998de

Model save

Browse files
Files changed (2) hide show
  1. README.md +171 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model: nguyenvulebinh/wav2vec2-base-vietnamese-250h
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: w2v2_ablation_with_ling_head-0drop-load-best-per-best_on_tp0.025_tl10_fp0.001_fl16
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
+ # w2v2_ablation_with_ling_head-0drop-load-best-per-best_on_tp0.025_tl10_fp0.001_fl16
17
+
18
+ This model is a fine-tuned version of [nguyenvulebinh/wav2vec2-base-vietnamese-250h](https://huggingface.co/nguyenvulebinh/wav2vec2-base-vietnamese-250h) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.4603
21
+ - Wer: 0.1849
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 32
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - total_train_batch_size: 32
47
+ - total_eval_batch_size: 128
48
+ - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_ratio: 0.1
51
+ - num_epochs: 100
52
+ - mixed_precision_training: Native AMP
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
57
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|
58
+ | 114.032 | 0.94 | 100 | 98.5210 | 21.4967 |
59
+ | 63.4912 | 1.89 | 200 | 9.8990 | 1.0 |
60
+ | 5.9426 | 2.83 | 300 | 5.2909 | 1.0 |
61
+ | 5.0183 | 3.77 | 400 | 5.2482 | 1.0 |
62
+ | 4.6782 | 4.72 | 500 | 5.5314 | 1.0 |
63
+ | 4.4732 | 5.66 | 600 | 5.2250 | 1.0 |
64
+ | 4.4059 | 6.6 | 700 | 5.1483 | 1.0 |
65
+ | 4.3368 | 7.55 | 800 | 4.9275 | 1.0 |
66
+ | 4.2178 | 8.49 | 900 | 4.8987 | 1.0 |
67
+ | 3.913 | 9.43 | 1000 | 3.7007 | 0.8807 |
68
+ | 2.7998 | 10.38 | 1100 | 2.1296 | 0.5331 |
69
+ | 1.8405 | 11.32 | 1200 | 1.4873 | 0.4636 |
70
+ | 1.2987 | 12.26 | 1300 | 1.0532 | 0.3338 |
71
+ | 1.0387 | 13.21 | 1400 | 0.8759 | 0.3348 |
72
+ | 0.851 | 14.15 | 1500 | 0.7743 | 0.3604 |
73
+ | 0.7128 | 15.09 | 1600 | 0.6523 | 0.2796 |
74
+ | 0.605 | 16.04 | 1700 | 0.6352 | 0.2995 |
75
+ | 0.5315 | 16.98 | 1800 | 0.5920 | 0.2603 |
76
+ | 0.4845 | 17.92 | 1900 | 0.5476 | 0.2503 |
77
+ | 0.4257 | 18.87 | 2000 | 0.5398 | 0.2285 |
78
+ | 0.4124 | 19.81 | 2100 | 0.5378 | 0.2764 |
79
+ | 0.3595 | 20.75 | 2200 | 0.5109 | 0.2147 |
80
+ | 0.3958 | 21.7 | 2300 | 0.4825 | 0.2342 |
81
+ | 0.3546 | 22.64 | 2400 | 0.4649 | 0.2251 |
82
+ | 0.304 | 23.58 | 2500 | 0.4701 | 0.2115 |
83
+ | 0.291 | 24.53 | 2600 | 0.4515 | 0.2180 |
84
+ | 0.2946 | 25.47 | 2700 | 0.4537 | 0.2012 |
85
+ | 0.2588 | 26.42 | 2800 | 0.4423 | 0.1939 |
86
+ | 0.2625 | 27.36 | 2900 | 0.4493 | 0.1924 |
87
+ | 0.2385 | 28.3 | 3000 | 0.4364 | 0.1724 |
88
+ | 0.2327 | 29.25 | 3100 | 0.4382 | 0.1967 |
89
+ | 0.26 | 30.19 | 3200 | 0.4454 | 0.1823 |
90
+ | 0.2151 | 31.13 | 3300 | 0.4424 | 0.1987 |
91
+ | 0.2213 | 32.08 | 3400 | 0.4377 | 0.2085 |
92
+ | 0.2226 | 33.02 | 3500 | 0.4375 | 0.2095 |
93
+ | 0.208 | 33.96 | 3600 | 0.4358 | 0.1994 |
94
+ | 0.2061 | 34.91 | 3700 | 0.4308 | 0.1919 |
95
+ | 0.1929 | 35.85 | 3800 | 0.4298 | 0.1905 |
96
+ | 0.1786 | 36.79 | 3900 | 0.4139 | 0.1974 |
97
+ | 0.172 | 37.74 | 4000 | 0.4183 | 0.1823 |
98
+ | 0.1769 | 38.68 | 4100 | 0.4252 | 0.1890 |
99
+ | 0.1813 | 39.62 | 4200 | 0.4360 | 0.1880 |
100
+ | 0.1676 | 40.57 | 4300 | 0.4325 | 0.1770 |
101
+ | 0.1581 | 41.51 | 4400 | 0.4386 | 0.1755 |
102
+ | 0.17 | 42.45 | 4500 | 0.4374 | 0.1979 |
103
+ | 0.1778 | 43.4 | 4600 | 0.4360 | 0.1726 |
104
+ | 0.162 | 44.34 | 4700 | 0.4424 | 0.1822 |
105
+ | 0.1605 | 45.28 | 4800 | 0.4500 | 0.2065 |
106
+ | 0.1472 | 46.23 | 4900 | 0.4555 | 0.2102 |
107
+ | 0.1428 | 47.17 | 5000 | 0.4358 | 0.1733 |
108
+ | 0.1393 | 48.11 | 5100 | 0.4406 | 0.1904 |
109
+ | 0.1444 | 49.06 | 5200 | 0.4481 | 0.2030 |
110
+ | 0.1401 | 50.0 | 5300 | 0.4507 | 0.1952 |
111
+ | 0.1311 | 50.94 | 5400 | 0.4353 | 0.1857 |
112
+ | 0.1337 | 51.89 | 5500 | 0.4439 | 0.2018 |
113
+ | 0.1289 | 52.83 | 5600 | 0.4461 | 0.1946 |
114
+ | 0.1234 | 53.77 | 5700 | 0.4395 | 0.2048 |
115
+ | 0.1301 | 54.72 | 5800 | 0.4590 | 0.2114 |
116
+ | 0.1378 | 55.66 | 5900 | 0.4548 | 0.2144 |
117
+ | 0.1251 | 56.6 | 6000 | 0.4477 | 0.1877 |
118
+ | 0.1224 | 57.55 | 6100 | 0.4478 | 0.1933 |
119
+ | 0.1233 | 58.49 | 6200 | 0.4467 | 0.1841 |
120
+ | 0.1237 | 59.43 | 6300 | 0.4399 | 0.1834 |
121
+ | 0.1176 | 60.38 | 6400 | 0.4471 | 0.2097 |
122
+ | 0.1117 | 61.32 | 6500 | 0.4587 | 0.1970 |
123
+ | 0.111 | 62.26 | 6600 | 0.4707 | 0.2102 |
124
+ | 0.1239 | 63.21 | 6700 | 0.4518 | 0.1923 |
125
+ | 0.1152 | 64.15 | 6800 | 0.4503 | 0.1967 |
126
+ | 0.1121 | 65.09 | 6900 | 0.4467 | 0.1944 |
127
+ | 0.1175 | 66.04 | 7000 | 0.4486 | 0.1914 |
128
+ | 0.1242 | 66.98 | 7100 | 0.4537 | 0.1973 |
129
+ | 0.111 | 67.92 | 7200 | 0.4587 | 0.2008 |
130
+ | 0.1063 | 68.87 | 7300 | 0.4551 | 0.1929 |
131
+ | 0.1133 | 69.81 | 7400 | 0.4547 | 0.1929 |
132
+ | 0.1098 | 70.75 | 7500 | 0.4512 | 0.1982 |
133
+ | 0.1123 | 71.7 | 7600 | 0.4578 | 0.1955 |
134
+ | 0.1144 | 72.64 | 7700 | 0.4533 | 0.1830 |
135
+ | 0.1113 | 73.58 | 7800 | 0.4545 | 0.1788 |
136
+ | 0.0968 | 74.53 | 7900 | 0.4584 | 0.1725 |
137
+ | 0.0951 | 75.47 | 8000 | 0.4646 | 0.1859 |
138
+ | 0.0982 | 76.42 | 8100 | 0.4557 | 0.1813 |
139
+ | 0.0959 | 77.36 | 8200 | 0.4566 | 0.1742 |
140
+ | 0.093 | 78.3 | 8300 | 0.4604 | 0.1880 |
141
+ | 0.103 | 79.25 | 8400 | 0.4614 | 0.1908 |
142
+ | 0.1101 | 80.19 | 8500 | 0.4586 | 0.1805 |
143
+ | 0.1046 | 81.13 | 8600 | 0.4590 | 0.1825 |
144
+ | 0.0979 | 82.08 | 8700 | 0.4555 | 0.1762 |
145
+ | 0.103 | 83.02 | 8800 | 0.4573 | 0.1780 |
146
+ | 0.0958 | 83.96 | 8900 | 0.4575 | 0.1803 |
147
+ | 0.0948 | 84.91 | 9000 | 0.4581 | 0.1814 |
148
+ | 0.1003 | 85.85 | 9100 | 0.4600 | 0.1830 |
149
+ | 0.1066 | 86.79 | 9200 | 0.4609 | 0.1870 |
150
+ | 0.0887 | 87.74 | 9300 | 0.4615 | 0.1834 |
151
+ | 0.0936 | 88.68 | 9400 | 0.4610 | 0.1819 |
152
+ | 0.0892 | 89.62 | 9500 | 0.4595 | 0.1801 |
153
+ | 0.1039 | 90.57 | 9600 | 0.4612 | 0.1837 |
154
+ | 0.097 | 91.51 | 9700 | 0.4610 | 0.1834 |
155
+ | 0.0969 | 92.45 | 9800 | 0.4605 | 0.1844 |
156
+ | 0.0946 | 93.4 | 9900 | 0.4596 | 0.1843 |
157
+ | 0.0947 | 94.34 | 10000 | 0.4605 | 0.1850 |
158
+ | 0.095 | 95.28 | 10100 | 0.4616 | 0.1861 |
159
+ | 0.0856 | 96.23 | 10200 | 0.4611 | 0.1853 |
160
+ | 0.0983 | 97.17 | 10300 | 0.4603 | 0.1850 |
161
+ | 0.0947 | 98.11 | 10400 | 0.4605 | 0.1853 |
162
+ | 0.0948 | 99.06 | 10500 | 0.4604 | 0.1853 |
163
+ | 0.0917 | 100.0 | 10600 | 0.4603 | 0.1849 |
164
+
165
+
166
+ ### Framework versions
167
+
168
+ - Transformers 4.35.2
169
+ - Pytorch 1.13.1+cu117
170
+ - Datasets 2.12.0
171
+ - Tokenizers 0.14.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:710e7c4389e08b65ab3aa9539940508176fb5dfba164ddc300384505acf24b21
3
  size 197617854
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03bb8440df115c41c48d668a745e2019f1fd80df35c3bea47c702f07bbe0a200
3
  size 197617854