Hugging Face's logo

charris
/
wav2vecvanilla_load_best

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
charris commited on
Commit
20d9381
•
1 Parent(s): e1c147f

End of training

Browse files
Files changed (2) hide show
  1. README.md +106 -0
  2. runs/Apr12_19-52-18_720442df35c8/events.out.tfevents.1712951721.720442df35c8.16846.0 +2 -2
README.md ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-base-960h
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: wav2vecvanilla_load_best
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # wav2vecvanilla_load_best
17
+
18
+ This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: nan
21
+ - Wer: 1.0
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0001
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 500
47
+ - num_epochs: 20
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | 1.47 | 0.43 | 100 | 1.0582 | 0.4027 |
54
+ | 1.2584 | 0.85 | 200 | 0.9775 | 0.3719 |
55
+ | 1.1377 | 1.28 | 300 | 0.9759 | 0.3628 |
56
+ | 1.0955 | 1.71 | 400 | 1.1271 | 0.3626 |
57
+ | 1.0945 | 2.14 | 500 | 0.9063 | 0.3589 |
58
+ | 1.0567 | 2.56 | 600 | 0.9288 | 0.3564 |
59
+ | 1.033 | 2.99 | 700 | 1.1634 | 0.3522 |
60
+ | 1.0043 | 3.42 | 800 | 0.8396 | 0.3506 |
61
+ | 0.9776 | 3.85 | 900 | 0.8654 | 0.3437 |
62
+ | 0.9147 | 4.27 | 1000 | 0.8816 | 0.3362 |
63
+ | 0.9041 | 4.7 | 1100 | 0.8994 | 0.3303 |
64
+ | 0.8648 | 5.13 | 1200 | 0.8379 | 0.3361 |
65
+ | 0.8241 | 5.56 | 1300 | 0.8263 | 0.3292 |
66
+ | 0.8716 | 5.98 | 1400 | 0.8350 | 0.3249 |
67
+ | 0.8218 | 6.41 | 1500 | nan | 1.0 |
68
+ | 0.0 | 6.84 | 1600 | nan | 1.0 |
69
+ | 0.0 | 7.26 | 1700 | nan | 1.0 |
70
+ | 0.0 | 7.69 | 1800 | nan | 1.0 |
71
+ | 0.0 | 8.12 | 1900 | nan | 1.0 |
72
+ | 0.0 | 8.55 | 2000 | nan | 1.0 |
73
+ | 0.0 | 8.97 | 2100 | nan | 1.0 |
74
+ | 0.0 | 9.4 | 2200 | nan | 1.0 |
75
+ | 0.0 | 9.83 | 2300 | nan | 1.0 |
76
+ | 0.0 | 10.26 | 2400 | nan | 1.0 |
77
+ | 0.0 | 10.68 | 2500 | nan | 1.0 |
78
+ | 0.0 | 11.11 | 2600 | nan | 1.0 |
79
+ | 0.0 | 11.54 | 2700 | nan | 1.0 |
80
+ | 0.0 | 11.97 | 2800 | nan | 1.0 |
81
+ | 0.0 | 12.39 | 2900 | nan | 1.0 |
82
+ | 0.0 | 12.82 | 3000 | nan | 1.0 |
83
+ | 0.0 | 13.25 | 3100 | nan | 1.0 |
84
+ | 0.0 | 13.68 | 3200 | nan | 1.0 |
85
+ | 0.0 | 14.1 | 3300 | nan | 1.0 |
86
+ | 0.0 | 14.53 | 3400 | nan | 1.0 |
87
+ | 0.0 | 14.96 | 3500 | nan | 1.0 |
88
+ | 0.0 | 15.38 | 3600 | nan | 1.0 |
89
+ | 0.0 | 15.81 | 3700 | nan | 1.0 |
90
+ | 0.0 | 16.24 | 3800 | nan | 1.0 |
91
+ | 0.0 | 16.67 | 3900 | nan | 1.0 |
92
+ | 0.0 | 17.09 | 4000 | nan | 1.0 |
93
+ | 0.0 | 17.52 | 4100 | nan | 1.0 |
94
+ | 0.0 | 17.95 | 4200 | nan | 1.0 |
95
+ | 0.0 | 18.38 | 4300 | nan | 1.0 |
96
+ | 0.0 | 18.8 | 4400 | nan | 1.0 |
97
+ | 0.0 | 19.23 | 4500 | nan | 1.0 |
98
+ | 0.0 | 19.66 | 4600 | nan | 1.0 |
99
+
100
+
101
+ ### Framework versions
102
+
103
+ - Transformers 4.38.2
104
+ - Pytorch 2.2.1+cu121
105
+ - Datasets 2.18.0
106
+ - Tokenizers 0.15.2
runs/Apr12_19-52-18_720442df35c8/events.out.tfevents.1712951721.720442df35c8.16846.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9986505c761e03db13eab319edeb7723a9097e2790fa7b0056fcab30f3740c9
3
- size 30354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8b4ed4b3ecd436b4818db6accc6144d06f1cd3bfaa15aa70c6c6dbe7318e03d
3
+ size 30708