sanchit-gandhi HF staff commited on
Commit
234a471
1 Parent(s): 98c9113

update model card README.md

Browse files
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 1.8529
19
+ - Wer: 0.9977
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: 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: 20.0
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
54
+ | 3.5506 | 2.8 | 2500 | 4.4928 | 1.8772 |
55
+ | 0.5145 | 5.61 | 5000 | 1.8942 | 1.1063 |
56
+ | 0.2736 | 8.41 | 7500 | 1.6550 | 1.0372 |
57
+ | 0.0807 | 11.21 | 10000 | 1.7601 | 1.0004 |
58
+ | 0.0439 | 14.01 | 12500 | 1.8014 | 1.0022 |
59
+ | 0.043 | 16.82 | 15000 | 1.8534 | 1.0097 |
60
+ | 0.0434 | 19.62 | 17500 | 1.8529 | 0.9977 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - Transformers 4.17.0.dev0
66
+ - Pytorch 1.10.2+cu113
67
+ - Datasets 1.18.3
68
+ - Tokenizers 0.11.0
wandb/run-20220318_085757-9419yrth/files/output.log CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b08d1ea7828bc89284e24e59f48fa848538b5be68df3bad4adc22ef2040e83d9
3
- size 30396294
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ff94688f3d81df17ff83d2d4116b1c37bec626b908f793efce8c2676ace4e31
3
+ size 30432829
wandb/run-20220318_085757-9419yrth/logs/debug-internal.log CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6414b882162b731972ddc5cb031425b85890e7a14a3c8932c207d41df3e3594
3
- size 28636502
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:662b8a2acf23272795e423dc15c5b4253b11888ff79472af5a14819ca00b879e
3
+ size 28657032
wandb/run-20220318_085757-9419yrth/run-9419yrth.wandb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a66e582012d1def7dd44040c1bb479a5bd7bd767b5933dd69cb51e40cb5b59de
3
- size 1088058226
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b85c98b024c8545a14dc7fc4757249446bbcbe78e96daeaa57ab1d09765b402
3
+ size 1088106299