Hugging Face's logo

lilitket
/
20220517-150219

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
lilitket commited on
Commit
bb9f277
•
1 Parent(s): cbc023e

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +166 -0
README.md ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: 20220517-150219
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # 20220517-150219
14
+
15
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.2426
18
+ - Wer: 0.2344
19
+ - Cer: 0.0434
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 8
41
+ - seed: 1339
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_steps: 100
45
+ - num_epochs: 2
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
50
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
51
+ | 5.3867 | 0.02 | 200 | 3.2171 | 1.0 | 1.0 |
52
+ | 3.1288 | 0.04 | 400 | 2.9394 | 1.0 | 1.0 |
53
+ | 1.8298 | 0.06 | 600 | 0.9138 | 0.8416 | 0.2039 |
54
+ | 0.9751 | 0.07 | 800 | 0.6568 | 0.6928 | 0.1566 |
55
+ | 0.7934 | 0.09 | 1000 | 0.5314 | 0.6225 | 0.1277 |
56
+ | 0.663 | 0.11 | 1200 | 0.4759 | 0.5730 | 0.1174 |
57
+ | 0.617 | 0.13 | 1400 | 0.4515 | 0.5578 | 0.1118 |
58
+ | 0.5473 | 0.15 | 1600 | 0.4017 | 0.5157 | 0.1004 |
59
+ | 0.5283 | 0.17 | 1800 | 0.3872 | 0.5094 | 0.0982 |
60
+ | 0.4893 | 0.18 | 2000 | 0.3725 | 0.4860 | 0.0932 |
61
+ | 0.495 | 0.2 | 2200 | 0.3580 | 0.4542 | 0.0878 |
62
+ | 0.4438 | 0.22 | 2400 | 0.3443 | 0.4366 | 0.0858 |
63
+ | 0.4425 | 0.24 | 2600 | 0.3428 | 0.4284 | 0.0865 |
64
+ | 0.4293 | 0.26 | 2800 | 0.3329 | 0.4221 | 0.0819 |
65
+ | 0.3779 | 0.28 | 3000 | 0.3278 | 0.4146 | 0.0794 |
66
+ | 0.4116 | 0.29 | 3200 | 0.3242 | 0.4107 | 0.0757 |
67
+ | 0.3912 | 0.31 | 3400 | 0.3217 | 0.4040 | 0.0776 |
68
+ | 0.391 | 0.33 | 3600 | 0.3127 | 0.3955 | 0.0764 |
69
+ | 0.3696 | 0.35 | 3800 | 0.3153 | 0.3892 | 0.0748 |
70
+ | 0.3576 | 0.37 | 4000 | 0.3156 | 0.3846 | 0.0737 |
71
+ | 0.3553 | 0.39 | 4200 | 0.3024 | 0.3814 | 0.0726 |
72
+ | 0.3394 | 0.4 | 4400 | 0.3022 | 0.3637 | 0.0685 |
73
+ | 0.3345 | 0.42 | 4600 | 0.3130 | 0.3641 | 0.0698 |
74
+ | 0.3357 | 0.44 | 4800 | 0.2913 | 0.3602 | 0.0701 |
75
+ | 0.3411 | 0.46 | 5000 | 0.2941 | 0.3514 | 0.0674 |
76
+ | 0.3031 | 0.48 | 5200 | 0.3043 | 0.3613 | 0.0685 |
77
+ | 0.3305 | 0.5 | 5400 | 0.2967 | 0.3468 | 0.0657 |
78
+ | 0.3004 | 0.51 | 5600 | 0.2723 | 0.3309 | 0.0616 |
79
+ | 0.31 | 0.53 | 5800 | 0.2835 | 0.3404 | 0.0648 |
80
+ | 0.3224 | 0.55 | 6000 | 0.2743 | 0.3358 | 0.0622 |
81
+ | 0.3261 | 0.57 | 6200 | 0.2803 | 0.3358 | 0.0620 |
82
+ | 0.305 | 0.59 | 6400 | 0.2835 | 0.3397 | 0.0629 |
83
+ | 0.3025 | 0.61 | 6600 | 0.2684 | 0.3340 | 0.0639 |
84
+ | 0.2952 | 0.62 | 6800 | 0.2654 | 0.3256 | 0.0617 |
85
+ | 0.2903 | 0.64 | 7000 | 0.2588 | 0.3174 | 0.0596 |
86
+ | 0.2907 | 0.66 | 7200 | 0.2789 | 0.3256 | 0.0623 |
87
+ | 0.2887 | 0.68 | 7400 | 0.2634 | 0.3142 | 0.0605 |
88
+ | 0.291 | 0.7 | 7600 | 0.2644 | 0.3097 | 0.0582 |
89
+ | 0.2646 | 0.72 | 7800 | 0.2753 | 0.3089 | 0.0582 |
90
+ | 0.2683 | 0.73 | 8000 | 0.2703 | 0.3036 | 0.0574 |
91
+ | 0.2808 | 0.75 | 8200 | 0.2544 | 0.2994 | 0.0561 |
92
+ | 0.2724 | 0.77 | 8400 | 0.2584 | 0.3051 | 0.0592 |
93
+ | 0.2516 | 0.79 | 8600 | 0.2575 | 0.2959 | 0.0557 |
94
+ | 0.2561 | 0.81 | 8800 | 0.2594 | 0.2945 | 0.0552 |
95
+ | 0.264 | 0.83 | 9000 | 0.2607 | 0.2987 | 0.0552 |
96
+ | 0.2383 | 0.84 | 9200 | 0.2641 | 0.2983 | 0.0546 |
97
+ | 0.2548 | 0.86 | 9400 | 0.2714 | 0.2930 | 0.0538 |
98
+ | 0.2284 | 0.88 | 9600 | 0.2542 | 0.2945 | 0.0555 |
99
+ | 0.2354 | 0.9 | 9800 | 0.2564 | 0.2937 | 0.0551 |
100
+ | 0.2624 | 0.92 | 10000 | 0.2466 | 0.2891 | 0.0542 |
101
+ | 0.24 | 0.94 | 10200 | 0.2404 | 0.2895 | 0.0528 |
102
+ | 0.2372 | 0.95 | 10400 | 0.2590 | 0.2782 | 0.0518 |
103
+ | 0.2357 | 0.97 | 10600 | 0.2629 | 0.2867 | 0.0531 |
104
+ | 0.2439 | 0.99 | 10800 | 0.2722 | 0.2902 | 0.0556 |
105
+ | 0.2204 | 1.01 | 11000 | 0.2618 | 0.2856 | 0.0535 |
106
+ | 0.2043 | 1.03 | 11200 | 0.2662 | 0.2789 | 0.0520 |
107
+ | 0.2081 | 1.05 | 11400 | 0.2744 | 0.2831 | 0.0532 |
108
+ | 0.199 | 1.06 | 11600 | 0.2586 | 0.2800 | 0.0519 |
109
+ | 0.2063 | 1.08 | 11800 | 0.2711 | 0.2842 | 0.0531 |
110
+ | 0.2116 | 1.1 | 12000 | 0.2463 | 0.2782 | 0.0529 |
111
+ | 0.2095 | 1.12 | 12200 | 0.2371 | 0.2757 | 0.0510 |
112
+ | 0.1786 | 1.14 | 12400 | 0.2693 | 0.2768 | 0.0520 |
113
+ | 0.1999 | 1.16 | 12600 | 0.2625 | 0.2793 | 0.0513 |
114
+ | 0.1985 | 1.17 | 12800 | 0.2734 | 0.2796 | 0.0532 |
115
+ | 0.187 | 1.19 | 13000 | 0.2654 | 0.2676 | 0.0514 |
116
+ | 0.188 | 1.21 | 13200 | 0.2548 | 0.2648 | 0.0489 |
117
+ | 0.1853 | 1.23 | 13400 | 0.2684 | 0.2641 | 0.0509 |
118
+ | 0.197 | 1.25 | 13600 | 0.2589 | 0.2662 | 0.0507 |
119
+ | 0.1873 | 1.27 | 13800 | 0.2633 | 0.2686 | 0.0516 |
120
+ | 0.179 | 1.28 | 14000 | 0.2682 | 0.2598 | 0.0508 |
121
+ | 0.2008 | 1.3 | 14200 | 0.2505 | 0.2609 | 0.0493 |
122
+ | 0.1802 | 1.32 | 14400 | 0.2470 | 0.2598 | 0.0493 |
123
+ | 0.1903 | 1.34 | 14600 | 0.2572 | 0.2672 | 0.0500 |
124
+ | 0.1852 | 1.36 | 14800 | 0.2576 | 0.2633 | 0.0491 |
125
+ | 0.1933 | 1.38 | 15000 | 0.2649 | 0.2602 | 0.0493 |
126
+ | 0.191 | 1.4 | 15200 | 0.2578 | 0.2612 | 0.0484 |
127
+ | 0.1863 | 1.41 | 15400 | 0.2572 | 0.2566 | 0.0488 |
128
+ | 0.1785 | 1.43 | 15600 | 0.2661 | 0.2520 | 0.0478 |
129
+ | 0.1755 | 1.45 | 15800 | 0.2637 | 0.2605 | 0.0485 |
130
+ | 0.1677 | 1.47 | 16000 | 0.2481 | 0.2559 | 0.0478 |
131
+ | 0.1633 | 1.49 | 16200 | 0.2584 | 0.2531 | 0.0476 |
132
+ | 0.166 | 1.51 | 16400 | 0.2576 | 0.2595 | 0.0487 |
133
+ | 0.1798 | 1.52 | 16600 | 0.2517 | 0.2570 | 0.0488 |
134
+ | 0.1879 | 1.54 | 16800 | 0.2555 | 0.2531 | 0.0479 |
135
+ | 0.1636 | 1.56 | 17000 | 0.2419 | 0.2467 | 0.0464 |
136
+ | 0.1706 | 1.58 | 17200 | 0.2426 | 0.2457 | 0.0463 |
137
+ | 0.1763 | 1.6 | 17400 | 0.2427 | 0.2496 | 0.0467 |
138
+ | 0.1687 | 1.62 | 17600 | 0.2507 | 0.2496 | 0.0467 |
139
+ | 0.1662 | 1.63 | 17800 | 0.2553 | 0.2474 | 0.0466 |
140
+ | 0.1637 | 1.65 | 18000 | 0.2576 | 0.2450 | 0.0461 |
141
+ | 0.1744 | 1.67 | 18200 | 0.2394 | 0.2414 | 0.0454 |
142
+ | 0.1597 | 1.69 | 18400 | 0.2442 | 0.2443 | 0.0452 |
143
+ | 0.1606 | 1.71 | 18600 | 0.2488 | 0.2435 | 0.0453 |
144
+ | 0.1558 | 1.73 | 18800 | 0.2563 | 0.2464 | 0.0464 |
145
+ | 0.172 | 1.74 | 19000 | 0.2501 | 0.2411 | 0.0452 |
146
+ | 0.1594 | 1.76 | 19200 | 0.2481 | 0.2460 | 0.0458 |
147
+ | 0.1732 | 1.78 | 19400 | 0.2427 | 0.2414 | 0.0443 |
148
+ | 0.1706 | 1.8 | 19600 | 0.2367 | 0.2418 | 0.0446 |
149
+ | 0.1724 | 1.82 | 19800 | 0.2376 | 0.2390 | 0.0444 |
150
+ | 0.1621 | 1.84 | 20000 | 0.2430 | 0.2382 | 0.0438 |
151
+ | 0.1501 | 1.85 | 20200 | 0.2445 | 0.2404 | 0.0438 |
152
+ | 0.1526 | 1.87 | 20400 | 0.2472 | 0.2361 | 0.0436 |
153
+ | 0.1756 | 1.89 | 20600 | 0.2431 | 0.2400 | 0.0437 |
154
+ | 0.1598 | 1.91 | 20800 | 0.2472 | 0.2368 | 0.0439 |
155
+ | 0.1554 | 1.93 | 21000 | 0.2431 | 0.2347 | 0.0435 |
156
+ | 0.1354 | 1.95 | 21200 | 0.2427 | 0.2354 | 0.0438 |
157
+ | 0.1587 | 1.96 | 21400 | 0.2427 | 0.2347 | 0.0435 |
158
+ | 0.1541 | 1.98 | 21600 | 0.2426 | 0.2344 | 0.0434 |
159
+
160
+
161
+ ### Framework versions
162
+
163
+ - Transformers 4.18.0.dev0
164
+ - Pytorch 1.10.0+cu113
165
+ - Datasets 2.1.0
166
+ - Tokenizers 0.11.6