patrickvonplaten commited on
Commit
3f6db7b
1 Parent(s): 3a794ee

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +90 -0
README.md ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - automatic-speech-recognition
5
+ - librispeech_asr
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: sew-mid-100k-librispeech-clean-100h-ft
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # sew-mid-100k-librispeech-clean-100h-ft
16
+
17
+ This model is a fine-tuned version of [asapp/sew-mid-100k](https://huggingface.co/asapp/sew-mid-100k) on the LIBRISPEECH_ASR - CLEAN dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 3.9609
20
+ - Wer: 1.0
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 0.0003
40
+ - train_batch_size: 4
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - distributed_type: multi-GPU
44
+ - num_devices: 8
45
+ - total_train_batch_size: 32
46
+ - total_eval_batch_size: 64
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_steps: 500
50
+ - num_epochs: 3.0
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
56
+ |:-------------:|:-----:|:----:|:---------------:|:---:|
57
+ | 2.9558 | 0.11 | 100 | 2.9238 | 1.0 |
58
+ | 2.8978 | 0.22 | 200 | 2.9614 | 1.0 |
59
+ | 2.9267 | 0.34 | 300 | 3.3049 | 1.0 |
60
+ | 3.1351 | 0.45 | 400 | 2.9246 | 1.0 |
61
+ | 3.4365 | 0.56 | 500 | 4.2798 | 1.0 |
62
+ | 3.1861 | 0.67 | 600 | 4.0740 | 1.0 |
63
+ | 2.914 | 0.78 | 700 | 3.6876 | 1.0 |
64
+ | 3.0777 | 0.9 | 800 | 3.7421 | 1.0 |
65
+ | 2.8181 | 1.01 | 900 | 3.7825 | 1.0 |
66
+ | 2.8211 | 1.12 | 1000 | 3.9630 | 1.0 |
67
+ | 2.8209 | 1.23 | 1100 | 3.9605 | 1.0 |
68
+ | 2.8304 | 1.35 | 1200 | 3.7005 | 1.0 |
69
+ | 2.85 | 1.46 | 1300 | 3.5085 | 1.0 |
70
+ | 2.8509 | 1.57 | 1400 | 3.6157 | 1.0 |
71
+ | 2.8643 | 1.68 | 1500 | 3.5116 | 1.0 |
72
+ | 2.8265 | 1.79 | 1600 | 3.6322 | 1.0 |
73
+ | 2.8032 | 1.91 | 1700 | 4.0325 | 1.0 |
74
+ | 2.8053 | 2.02 | 1800 | 4.0125 | 1.0 |
75
+ | 2.819 | 2.13 | 1900 | 3.7971 | 1.0 |
76
+ | 2.8163 | 2.24 | 2000 | 3.9216 | 1.0 |
77
+ | 2.8214 | 2.35 | 2100 | 3.9178 | 1.0 |
78
+ | 2.8116 | 2.47 | 2200 | 3.9604 | 1.0 |
79
+ | 2.81 | 2.58 | 2300 | 3.9279 | 1.0 |
80
+ | 2.8051 | 2.69 | 2400 | 3.9737 | 1.0 |
81
+ | 2.8179 | 2.8 | 2500 | 3.9725 | 1.0 |
82
+ | 2.8098 | 2.91 | 2600 | 3.9591 | 1.0 |
83
+
84
+
85
+ ### Framework versions
86
+
87
+ - Transformers 4.12.0.dev0
88
+ - Pytorch 1.9.0+cu111
89
+ - Datasets 1.13.4.dev0
90
+ - Tokenizers 0.10.3