sanchit-gandhi HF staff commited on
Commit
bb49882
1 Parent(s): 7ed6ef7

update model card README.md

Browse files
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - librispeech_asr
6
+ model-index:
7
+ - name: ''
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ #
15
+
16
+ This model was trained from scratch on the librispeech_asr dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.6977
19
+ - Wer: 0.1231
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: 3e-05
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 32
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 1000
47
+ - num_epochs: 25.0
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
54
+ | 6.1467 | 1.68 | 1500 | 6.0558 | 1.3243 |
55
+ | 5.4388 | 3.36 | 3000 | 5.4711 | 1.5604 |
56
+ | 3.3434 | 5.04 | 4500 | 3.4808 | 0.7461 |
57
+ | 1.5259 | 6.73 | 6000 | 2.1931 | 0.3430 |
58
+ | 1.4285 | 8.41 | 7500 | 1.5883 | 0.2784 |
59
+ | 1.0687 | 10.09 | 9000 | 1.2481 | 0.2069 |
60
+ | 0.6425 | 11.77 | 10500 | 1.0507 | 0.1758 |
61
+ | 0.7147 | 13.45 | 12000 | 0.9397 | 0.1584 |
62
+ | 0.5083 | 15.13 | 13500 | 0.8452 | 0.1453 |
63
+ | 0.4287 | 16.82 | 15000 | 0.7915 | 0.1388 |
64
+ | 0.3499 | 18.5 | 16500 | 0.7477 | 0.1315 |
65
+ | 0.3733 | 20.18 | 18000 | 0.7307 | 0.1287 |
66
+ | 0.2609 | 21.86 | 19500 | 0.7061 | 0.1263 |
67
+ | 0.2602 | 23.54 | 21000 | 0.6977 | 0.1231 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - Transformers 4.17.0.dev0
73
+ - Pytorch 1.10.2+cu113
74
+ - Datasets 1.18.3
75
+ - Tokenizers 0.11.0
wandb/run-20220324_170224-3nn5zxhl/files/output.log CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68c7873fea005fc0fb611f2f241fa5173fc6829555dd903c239b9c57e6c50df8
3
- size 37175868
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:616584b0ce2d05f706ea14a127d67dabc61b8380011722819e584d9ead756e9d
3
+ size 37212248
wandb/run-20220324_170224-3nn5zxhl/logs/debug-internal.log CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17ecbd7e15d8696ae15efb0ec8297f54fe130ed02e58f355f92cb731dbcc97c8
3
- size 35987802
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab3ac67357b41e8b1fea1e3f9606d7b20bd3a6cf1218fda5ec2aa908a22f7760
3
+ size 36008044
wandb/run-20220324_170224-3nn5zxhl/run-3nn5zxhl.wandb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5875465a83e965257d3e20413169498462eb341187917bb55a8bddd51d3af336
3
- size 1092449734
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66a60d17bddaef18a290d58832b3dbd41b5b758218c876dec8f9fdf425a47bf5
3
+ size 1092518386