Hugging Face's logo

tinybee
/
gopdataset_phonome_base

PyTorch
wav2vec2
Generated from Trainer
Model card Files Community
tinybee commited on
Commit
520b049
·
1 Parent(s): ffcf3bb

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +93 -0
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: gopdataset_phonome_base
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
+ # gopdataset_phonome_base
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: 0.2722
18
+ - Cer: 0.1144
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0001
38
+ - train_batch_size: 32
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - lr_scheduler_warmup_steps: 1000
44
+ - num_epochs: 30
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Cer |
50
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
51
+ | 10.4672 | 0.84 | 100 | 12.3501 | 0.9750 |
52
+ | 5.6053 | 1.68 | 200 | 4.4724 | 0.9750 |
53
+ | 3.6779 | 2.52 | 300 | 3.5514 | 0.9750 |
54
+ | 3.3108 | 3.36 | 400 | 3.4045 | 0.9750 |
55
+ | 3.2684 | 4.2 | 500 | 3.4435 | 0.7828 |
56
+ | 3.1223 | 5.04 | 600 | 3.0123 | 0.7864 |
57
+ | 2.663 | 5.88 | 700 | 2.1177 | 0.6216 |
58
+ | 1.8146 | 6.72 | 800 | 0.9518 | 0.2387 |
59
+ | 1.0305 | 7.56 | 900 | 0.5432 | 0.1662 |
60
+ | 0.7835 | 8.4 | 1000 | 0.4268 | 0.1500 |
61
+ | 0.6468 | 9.24 | 1100 | 0.3911 | 0.1422 |
62
+ | 0.564 | 10.08 | 1200 | 0.3544 | 0.1378 |
63
+ | 0.5089 | 10.92 | 1300 | 0.3322 | 0.1356 |
64
+ | 0.4667 | 11.76 | 1400 | 0.3058 | 0.1277 |
65
+ | 0.4304 | 12.61 | 1500 | 0.2984 | 0.1248 |
66
+ | 0.4248 | 13.45 | 1600 | 0.3040 | 0.1270 |
67
+ | 0.4041 | 14.29 | 1700 | 0.2886 | 0.1223 |
68
+ | 0.3641 | 15.13 | 1800 | 0.2860 | 0.1215 |
69
+ | 0.3611 | 15.97 | 1900 | 0.2868 | 0.1220 |
70
+ | 0.3336 | 16.81 | 2000 | 0.2906 | 0.1217 |
71
+ | 0.3329 | 17.65 | 2100 | 0.2908 | 0.1213 |
72
+ | 0.3264 | 18.49 | 2200 | 0.2933 | 0.1204 |
73
+ | 0.3059 | 19.33 | 2300 | 0.2818 | 0.1193 |
74
+ | 0.2966 | 20.17 | 2400 | 0.2924 | 0.1196 |
75
+ | 0.2948 | 21.01 | 2500 | 0.2851 | 0.1186 |
76
+ | 0.2833 | 21.85 | 2600 | 0.2818 | 0.1181 |
77
+ | 0.2724 | 22.69 | 2700 | 0.2884 | 0.1183 |
78
+ | 0.2693 | 23.53 | 2800 | 0.2905 | 0.1179 |
79
+ | 0.2593 | 24.37 | 2900 | 0.2894 | 0.1184 |
80
+ | 0.2515 | 25.21 | 3000 | 0.2931 | 0.1169 |
81
+ | 0.2487 | 26.05 | 3100 | 0.2915 | 0.1176 |
82
+ | 0.2518 | 26.89 | 3200 | 0.2900 | 0.1176 |
83
+ | 0.2467 | 27.73 | 3300 | 0.2934 | 0.1175 |
84
+ | 0.246 | 28.57 | 3400 | 0.2965 | 0.1182 |
85
+ | 0.2537 | 29.41 | 3500 | 0.2948 | 0.1183 |
86
+
87
+
88
+ ### Framework versions
89
+
90
+ - Transformers 4.17.0
91
+ - Pytorch 2.4.0
92
+ - Datasets 1.18.3
93
+ - Tokenizers 0.20.3