dmusingu commited on
Commit
1db6d39
·
verified ·
1 Parent(s): ddbb8fa

End of training

Browse files
Files changed (1) hide show
  1. README.md +54 -2
README.md CHANGED
@@ -3,9 +3,26 @@ license: apache-2.0
3
  base_model: facebook/wav2vec2-xls-r-300m
4
  tags:
5
  - generated_from_trainer
 
 
 
 
6
  model-index:
7
  - name: XLS-R-LUGANDA-ASR-CV14
8
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -13,7 +30,11 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # XLS-R-LUGANDA-ASR-CV14
15
 
16
- This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
 
 
 
 
17
 
18
  ## Model description
19
 
@@ -44,6 +65,37 @@ The following hyperparameters were used during training:
44
  - training_steps: 10000
45
  - mixed_precision_training: Native AMP
46
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  ### Framework versions
48
 
49
  - Transformers 4.38.1
 
3
  base_model: facebook/wav2vec2-xls-r-300m
4
  tags:
5
  - generated_from_trainer
6
+ datasets:
7
+ - common_voice_14_0
8
+ metrics:
9
+ - wer
10
  model-index:
11
  - name: XLS-R-LUGANDA-ASR-CV14
12
+ results:
13
+ - task:
14
+ name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
+ dataset:
17
+ name: common_voice_14_0
18
+ type: common_voice_14_0
19
+ config: lg
20
+ split: test
21
+ args: lg
22
+ metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 0.2406197895094572
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
30
 
31
  # XLS-R-LUGANDA-ASR-CV14
32
 
33
+ 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_14_0 dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: inf
36
+ - Wer: 0.2406
37
+ - Cer: 0.0537
38
 
39
  ## Model description
40
 
 
65
  - training_steps: 10000
66
  - mixed_precision_training: Native AMP
67
 
68
+ ### Training results
69
+
70
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
71
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
72
+ | 4.24 | 0.18 | 400 | inf | 0.8354 | 0.2170 |
73
+ | 0.6124 | 0.36 | 800 | inf | 0.5690 | 0.1360 |
74
+ | 0.4411 | 0.54 | 1200 | inf | 0.4746 | 0.1120 |
75
+ | 0.3839 | 0.72 | 1600 | inf | 0.4409 | 0.1050 |
76
+ | 0.3504 | 0.9 | 2000 | inf | 0.3955 | 0.0943 |
77
+ | 0.3214 | 1.08 | 2400 | inf | 0.3678 | 0.0854 |
78
+ | 0.2879 | 1.26 | 2800 | inf | 0.3614 | 0.0836 |
79
+ | 0.284 | 1.45 | 3200 | inf | 0.3411 | 0.0789 |
80
+ | 0.2683 | 1.63 | 3600 | inf | 0.3362 | 0.0767 |
81
+ | 0.2572 | 1.81 | 4000 | inf | 0.3241 | 0.0740 |
82
+ | 0.2532 | 1.99 | 4400 | inf | 0.3117 | 0.0719 |
83
+ | 0.2228 | 2.17 | 4800 | inf | 0.2977 | 0.0677 |
84
+ | 0.2143 | 2.35 | 5200 | inf | 0.2969 | 0.0676 |
85
+ | 0.211 | 2.53 | 5600 | inf | 0.2918 | 0.0665 |
86
+ | 0.2066 | 2.71 | 6000 | inf | 0.2848 | 0.0647 |
87
+ | 0.2026 | 2.89 | 6400 | inf | 0.2804 | 0.0637 |
88
+ | 0.1898 | 3.07 | 6800 | inf | 0.2744 | 0.0627 |
89
+ | 0.1747 | 3.25 | 7200 | inf | 0.2668 | 0.0603 |
90
+ | 0.1667 | 3.43 | 7600 | inf | 0.2631 | 0.0597 |
91
+ | 0.1639 | 3.61 | 8000 | inf | 0.2558 | 0.0580 |
92
+ | 0.1601 | 3.79 | 8400 | inf | 0.2519 | 0.0567 |
93
+ | 0.1546 | 3.98 | 8800 | inf | 0.2487 | 0.0554 |
94
+ | 0.1395 | 4.16 | 9200 | inf | 0.2449 | 0.0551 |
95
+ | 0.1364 | 4.34 | 9600 | inf | 0.2425 | 0.0542 |
96
+ | 0.1341 | 4.52 | 10000 | inf | 0.2406 | 0.0537 |
97
+
98
+
99
  ### Framework versions
100
 
101
  - Transformers 4.38.1