tz579 commited on
Commit
70bbcc7
1 Parent(s): c12b474

Model save

Browse files
README.md ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-base
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - timit_asr
8
+ metrics:
9
+ - wer
10
+ model-index:
11
+ - name: wav2vec2-base-timit-fine-tuned
12
+ results:
13
+ - task:
14
+ name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
+ dataset:
17
+ name: timit_asr
18
+ type: timit_asr
19
+ config: clean
20
+ split: test
21
+ args: clean
22
+ metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 0.41728125284530637
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # wav2vec2-base-timit-fine-tuned
32
+
33
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the timit_asr dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.4273
36
+ - Wer: 0.4173
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 0.0001
56
+ - train_batch_size: 32
57
+ - eval_batch_size: 1
58
+ - seed: 42
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_steps: 1000
62
+ - num_epochs: 20.0
63
+ - mixed_precision_training: Native AMP
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
68
+ |:-------------:|:-------:|:----:|:---------------:|:------:|
69
+ | 3.1618 | 0.8621 | 100 | 3.1117 | 1.0 |
70
+ | 2.9798 | 1.7241 | 200 | 2.9736 | 1.0 |
71
+ | 2.9144 | 2.5862 | 300 | 2.9075 | 1.0 |
72
+ | 2.1714 | 3.4483 | 400 | 2.0945 | 1.0325 |
73
+ | 1.1579 | 4.3103 | 500 | 1.0451 | 0.8299 |
74
+ | 0.6087 | 5.1724 | 600 | 0.6754 | 0.6441 |
75
+ | 0.481 | 6.0345 | 700 | 0.5275 | 0.5761 |
76
+ | 0.3072 | 6.8966 | 800 | 0.4836 | 0.5264 |
77
+ | 0.332 | 7.7586 | 900 | 0.4403 | 0.5234 |
78
+ | 0.1876 | 8.6207 | 1000 | 0.4758 | 0.5222 |
79
+ | 0.2232 | 9.4828 | 1100 | 0.4508 | 0.4892 |
80
+ | 0.1332 | 10.3448 | 1200 | 0.4394 | 0.4740 |
81
+ | 0.1085 | 11.2069 | 1300 | 0.4466 | 0.4621 |
82
+ | 0.098 | 12.0690 | 1400 | 0.4230 | 0.4493 |
83
+ | 0.1219 | 12.9310 | 1500 | 0.4180 | 0.4460 |
84
+ | 0.1021 | 13.7931 | 1600 | 0.4179 | 0.4406 |
85
+ | 0.0741 | 14.6552 | 1700 | 0.4113 | 0.4309 |
86
+ | 0.0896 | 15.5172 | 1800 | 0.4392 | 0.4308 |
87
+ | 0.0492 | 16.3793 | 1900 | 0.4202 | 0.4313 |
88
+ | 0.0759 | 17.2414 | 2000 | 0.4348 | 0.4207 |
89
+ | 0.0406 | 18.1034 | 2100 | 0.4419 | 0.4205 |
90
+ | 0.074 | 18.9655 | 2200 | 0.4306 | 0.4200 |
91
+ | 0.0378 | 19.8276 | 2300 | 0.4273 | 0.4173 |
92
+
93
+
94
+ ### Framework versions
95
+
96
+ - Transformers 4.42.0.dev0
97
+ - Pytorch 2.3.0.post300
98
+ - Datasets 2.19.1
99
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b268b52f488a106b89f0c17a47ecd12dc515f7dc6c264a8fa34396b91dc97e03
3
  size 377608044
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff67ef936783355fa464ae72e951b2b3b15ba1294527b55db68acf606eea9768
3
  size 377608044
runs/May19_22-08-09_tz579-raptorlake/events.out.tfevents.1716174523.tz579-raptorlake.65634.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f80733427598f8a2fe41ebdb8d8440ed814db4fcabd4cbb07fb420e94a4d3720
3
- size 55109
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1499de7f8d44ad8690a4fee9818a4ec46085f303e71f1d916a3979f95334b4f
3
+ size 63169