Hugging Face's logo

jfealko
/
wav2vec2-large-xls-r-300m-irish-colab_test

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
jfealko commited on
Commit
e40276b
•
1 Parent(s): bb8a2c5

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +92 -0
README.md ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice
7
+ model-index:
8
+ - name: wav2vec2-large-xls-r-300m-irish-colab_test
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # wav2vec2-large-xls-r-300m-irish-colab_test
16
+
17
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.7839
20
+ - Wer: 0.6220
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 0.0003
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 32
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 100
48
+ - num_epochs: 90
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
55
+ | 10.0428 | 2.94 | 50 | 4.1311 | 1.0 |
56
+ | 3.2917 | 5.88 | 100 | 3.1468 | 1.0 |
57
+ | 3.0221 | 8.82 | 150 | 2.9848 | 1.0 |
58
+ | 2.9795 | 11.76 | 200 | 2.9567 | 1.0 |
59
+ | 2.9379 | 14.71 | 250 | 2.9463 | 1.0 |
60
+ | 2.9068 | 17.65 | 300 | 2.8330 | 1.0 |
61
+ | 2.5088 | 20.59 | 350 | 1.9807 | 0.9535 |
62
+ | 1.6188 | 23.53 | 400 | 1.4254 | 0.8398 |
63
+ | 1.0435 | 26.47 | 450 | 1.3668 | 0.7807 |
64
+ | 0.7212 | 29.41 | 500 | 1.3914 | 0.7476 |
65
+ | 0.5456 | 32.35 | 550 | 1.5495 | 0.7470 |
66
+ | 0.4297 | 35.29 | 600 | 1.4751 | 0.6960 |
67
+ | 0.3533 | 38.24 | 650 | 1.5157 | 0.6909 |
68
+ | 0.2899 | 41.18 | 700 | 1.5394 | 0.6879 |
69
+ | 0.2529 | 44.12 | 750 | 1.6186 | 0.6903 |
70
+ | 0.2413 | 47.06 | 800 | 1.6386 | 0.6954 |
71
+ | 0.2113 | 50.0 | 850 | 1.6906 | 0.6778 |
72
+ | 0.1769 | 52.94 | 900 | 1.6918 | 0.6575 |
73
+ | 0.1622 | 55.88 | 950 | 1.7313 | 0.6572 |
74
+ | 0.1564 | 58.82 | 1000 | 1.7701 | 0.6510 |
75
+ | 0.1637 | 61.76 | 1050 | 1.6800 | 0.6444 |
76
+ | 0.148 | 64.71 | 1100 | 1.7306 | 0.6477 |
77
+ | 0.1385 | 67.65 | 1150 | 1.7605 | 0.6408 |
78
+ | 0.1264 | 70.59 | 1200 | 1.7534 | 0.6244 |
79
+ | 0.1157 | 73.53 | 1250 | 1.7906 | 0.6381 |
80
+ | 0.1027 | 76.47 | 1300 | 1.7803 | 0.6265 |
81
+ | 0.1061 | 79.41 | 1350 | 1.7617 | 0.6259 |
82
+ | 0.0934 | 82.35 | 1400 | 1.7649 | 0.6253 |
83
+ | 0.0904 | 85.29 | 1450 | 1.7713 | 0.6187 |
84
+ | 0.0911 | 88.24 | 1500 | 1.7839 | 0.6220 |
85
+
86
+
87
+ ### Framework versions
88
+
89
+ - Transformers 4.11.3
90
+ - Pytorch 1.10.0+cu111
91
+ - Datasets 1.18.3
92
+ - Tokenizers 0.10.3