Hugging Face's logo

itaihay
/
wav2vec_asr_swbd_10_epochs

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Model card Files Metrics Community
itaihay commited on
Commit
ae1999c
·
1 Parent(s): d0d3a68

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +103 -0
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: wav2vec_asr_swbd_10_epochs
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
+ # wav2vec_asr_swbd_10_epochs
14
+
15
+ This model is a fine-tuned version of [facebook/wav2vec2-large-robust-ft-swbd-300h](https://huggingface.co/facebook/wav2vec2-large-robust-ft-swbd-300h) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: nan
18
+ - Wer: 0.9627
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: 8
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: 10
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
50
+ |:-------------:|:-----:|:------:|:---------------:|:------:|
51
+ | 1.0682 | 0.22 | 5000 | 0.7383 | 0.4431 |
52
+ | 0.9143 | 0.44 | 10000 | 0.7182 | 0.4058 |
53
+ | 0.8905 | 0.66 | 15000 | 0.6291 | 0.3987 |
54
+ | 0.8354 | 0.87 | 20000 | 0.5976 | 0.3954 |
55
+ | 0.7749 | 1.09 | 25000 | 0.5773 | 0.3901 |
56
+ | 0.7336 | 1.31 | 30000 | 0.5812 | 0.3871 |
57
+ | 0.7314 | 1.53 | 35000 | 0.5802 | 0.3895 |
58
+ | 0.0 | 1.75 | 40000 | nan | 0.9627 |
59
+ | 0.0 | 1.97 | 45000 | nan | 0.9627 |
60
+ | 0.0 | 2.19 | 50000 | nan | 0.9627 |
61
+ | 0.0 | 2.4 | 55000 | nan | 0.9627 |
62
+ | 0.0 | 2.62 | 60000 | nan | 0.9627 |
63
+ | 0.0 | 2.84 | 65000 | nan | 0.9627 |
64
+ | 0.0 | 3.06 | 70000 | nan | 0.9627 |
65
+ | 0.0 | 3.28 | 75000 | nan | 0.9627 |
66
+ | 0.0 | 3.5 | 80000 | nan | 0.9627 |
67
+ | 0.0 | 3.72 | 85000 | nan | 0.9627 |
68
+ | 0.0 | 3.93 | 90000 | nan | 0.9627 |
69
+ | 0.0 | 4.15 | 95000 | nan | 0.9627 |
70
+ | 0.0 | 4.37 | 100000 | nan | 0.9627 |
71
+ | 0.0 | 4.59 | 105000 | nan | 0.9627 |
72
+ | 0.0 | 4.81 | 110000 | nan | 0.9627 |
73
+ | 0.0 | 5.03 | 115000 | nan | 0.9627 |
74
+ | 0.0 | 5.25 | 120000 | nan | 0.9627 |
75
+ | 0.0 | 5.46 | 125000 | nan | 0.9627 |
76
+ | 0.0 | 5.68 | 130000 | nan | 0.9627 |
77
+ | 0.0 | 5.9 | 135000 | nan | 0.9627 |
78
+ | 0.0 | 6.12 | 140000 | nan | 0.9627 |
79
+ | 0.0 | 6.34 | 145000 | nan | 0.9627 |
80
+ | 0.0 | 6.56 | 150000 | nan | 0.9627 |
81
+ | 0.0 | 6.78 | 155000 | nan | 0.9627 |
82
+ | 0.0 | 7.0 | 160000 | nan | 0.9627 |
83
+ | 0.0 | 7.21 | 165000 | nan | 0.9627 |
84
+ | 0.0 | 7.43 | 170000 | nan | 0.9627 |
85
+ | 0.0 | 7.65 | 175000 | nan | 0.9627 |
86
+ | 0.0 | 7.87 | 180000 | nan | 0.9627 |
87
+ | 0.0 | 8.09 | 185000 | nan | 0.9627 |
88
+ | 0.0 | 8.31 | 190000 | nan | 0.9627 |
89
+ | 0.0 | 8.53 | 195000 | nan | 0.9627 |
90
+ | 0.0 | 8.74 | 200000 | nan | 0.9627 |
91
+ | 0.0 | 8.96 | 205000 | nan | 0.9627 |
92
+ | 0.0 | 9.18 | 210000 | nan | 0.9627 |
93
+ | 0.0 | 9.4 | 215000 | nan | 0.9627 |
94
+ | 0.0 | 9.62 | 220000 | nan | 0.9627 |
95
+ | 0.0 | 9.84 | 225000 | nan | 0.9627 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.17.0
101
+ - Pytorch 1.11.0+cu113
102
+ - Datasets 1.18.4
103
+ - Tokenizers 0.11.6