Gemmar commited on
Commit
542fce2
1 Parent(s): 39b94d0

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
+ datasets:
6
+ - common_voice_13_0
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: wav2vec2LugandaASR20
11
+ results:
12
+ - task:
13
+ name: Automatic Speech Recognition
14
+ type: automatic-speech-recognition
15
+ dataset:
16
+ name: common_voice_13_0
17
+ type: common_voice_13_0
18
+ config: lg
19
+ split: validation
20
+ args: lg
21
+ metrics:
22
+ - name: Wer
23
+ type: wer
24
+ value: 0.23221005634102265
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # wav2vec2LugandaASR20
31
+
32
+ This model is a fine-tuned version of [Gemmar/wav2vec2LugandaASR](https://huggingface.co/Gemmar/wav2vec2LugandaASR) on the common_voice_13_0 dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.2393
35
+ - Wer: 0.2322
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 0.0003
55
+ - train_batch_size: 32
56
+ - eval_batch_size: 8
57
+ - seed: 42
58
+ - gradient_accumulation_steps: 4
59
+ - total_train_batch_size: 128
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_steps: 200
63
+ - num_epochs: 5
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
68
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
69
+ | 0.1093 | 0.18 | 100 | 0.2134 | 0.2480 |
70
+ | 0.1141 | 0.36 | 200 | 0.2329 | 0.2724 |
71
+ | 0.1224 | 0.54 | 300 | 0.2560 | 0.2864 |
72
+ | 0.1345 | 0.72 | 400 | 0.2348 | 0.2716 |
73
+ | 0.1271 | 0.9 | 500 | 0.2339 | 0.2702 |
74
+ | 0.1232 | 1.08 | 600 | 0.2457 | 0.2806 |
75
+ | 0.1149 | 1.27 | 700 | 0.2372 | 0.2695 |
76
+ | 0.1129 | 1.45 | 800 | 0.2328 | 0.2718 |
77
+ | 0.1196 | 1.63 | 900 | 0.2326 | 0.2615 |
78
+ | 0.1185 | 1.81 | 1000 | 0.2249 | 0.2672 |
79
+ | 0.1159 | 1.99 | 1100 | 0.2202 | 0.2559 |
80
+ | 0.0933 | 2.17 | 1200 | 0.2302 | 0.2559 |
81
+ | 0.0947 | 2.35 | 1300 | 0.2306 | 0.2530 |
82
+ | 0.0941 | 2.53 | 1400 | 0.2325 | 0.2509 |
83
+ | 0.0946 | 2.71 | 1500 | 0.2233 | 0.2495 |
84
+ | 0.0949 | 2.89 | 1600 | 0.2320 | 0.2443 |
85
+ | 0.0883 | 3.07 | 1700 | 0.2383 | 0.2463 |
86
+ | 0.0783 | 3.25 | 1800 | 0.2386 | 0.2437 |
87
+ | 0.0753 | 3.43 | 1900 | 0.2329 | 0.2426 |
88
+ | 0.0772 | 3.62 | 2000 | 0.2317 | 0.2392 |
89
+ | 0.0774 | 3.8 | 2100 | 0.2308 | 0.2353 |
90
+ | 0.0764 | 3.98 | 2200 | 0.2293 | 0.2357 |
91
+ | 0.0666 | 4.16 | 2300 | 0.2446 | 0.2388 |
92
+ | 0.065 | 4.34 | 2400 | 0.2456 | 0.2359 |
93
+ | 0.0643 | 4.52 | 2500 | 0.2446 | 0.2345 |
94
+ | 0.0652 | 4.7 | 2600 | 0.2430 | 0.2325 |
95
+ | 0.0669 | 4.88 | 2700 | 0.2393 | 0.2322 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.30.2
101
+ - Pytorch 2.0.1+cu118
102
+ - Datasets 2.13.0
103
+ - Tokenizers 0.13.3