patrickvonplaten commited on
Commit
673405a
1 Parent(s): 635b5d0

update model card README.md

Browse files

Files changed (1) hide show
  1. README.md +91 -0
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - automatic-speech-recognition
5
+ - timit_asr
6
+ - generated_from_trainer
7
+ datasets:
8
+ - timit_asr
9
+ model-index:
10
+ - name: sew-small-100k-timit
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # sew-small-100k-timit
18
+
19
+ This model is a fine-tuned version of [asapp/sew-small-100k](https://huggingface.co/asapp/sew-small-100k) on the TIMIT_ASR - NA dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.4926
22
+ - Wer: 0.2988
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: 0.0001
42
+ - train_batch_size: 32
43
+ - eval_batch_size: 1
44
+ - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 1000
48
+ - num_epochs: 20.0
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
55
+ | 3.071 | 0.69 | 100 | 3.0262 | 1.0 |
56
+ | 2.9304 | 1.38 | 200 | 2.9297 | 1.0 |
57
+ | 2.8823 | 2.07 | 300 | 2.8367 | 1.0 |
58
+ | 1.5668 | 2.76 | 400 | 1.2310 | 0.8807 |
59
+ | 0.7422 | 3.45 | 500 | 0.7080 | 0.5957 |
60
+ | 0.4121 | 4.14 | 600 | 0.5829 | 0.5073 |
61
+ | 0.3981 | 4.83 | 700 | 0.5153 | 0.4461 |
62
+ | 0.5038 | 5.52 | 800 | 0.4908 | 0.4151 |
63
+ | 0.2899 | 6.21 | 900 | 0.5122 | 0.4111 |
64
+ | 0.2198 | 6.9 | 1000 | 0.4908 | 0.3803 |
65
+ | 0.2129 | 7.59 | 1100 | 0.4668 | 0.3789 |
66
+ | 0.3007 | 8.28 | 1200 | 0.4788 | 0.3562 |
67
+ | 0.2264 | 8.97 | 1300 | 0.5113 | 0.3635 |
68
+ | 0.1536 | 9.66 | 1400 | 0.4950 | 0.3441 |
69
+ | 0.1206 | 10.34 | 1500 | 0.5062 | 0.3421 |
70
+ | 0.2021 | 11.03 | 1600 | 0.4900 | 0.3283 |
71
+ | 0.1458 | 11.72 | 1700 | 0.5019 | 0.3307 |
72
+ | 0.1151 | 12.41 | 1800 | 0.4989 | 0.3270 |
73
+ | 0.0985 | 13.1 | 1900 | 0.4925 | 0.3173 |
74
+ | 0.1412 | 13.79 | 2000 | 0.4868 | 0.3125 |
75
+ | 0.1579 | 14.48 | 2100 | 0.4983 | 0.3147 |
76
+ | 0.1043 | 15.17 | 2200 | 0.4914 | 0.3091 |
77
+ | 0.0773 | 15.86 | 2300 | 0.4858 | 0.3102 |
78
+ | 0.1327 | 16.55 | 2400 | 0.5084 | 0.3064 |
79
+ | 0.1281 | 17.24 | 2500 | 0.5017 | 0.3025 |
80
+ | 0.0845 | 17.93 | 2600 | 0.5001 | 0.3012 |
81
+ | 0.0717 | 18.62 | 2700 | 0.4894 | 0.3004 |
82
+ | 0.0835 | 19.31 | 2800 | 0.4963 | 0.2998 |
83
+ | 0.1181 | 20.0 | 2900 | 0.4926 | 0.2988 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - Transformers 4.12.0.dev0
89
+ - Pytorch 1.8.1
90
+ - Datasets 1.14.1.dev0
91
+ - Tokenizers 0.10.3