macarious commited on
Commit
a40951f
·
1 Parent(s): 606d777

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +48 -6
README.md CHANGED
@@ -1,12 +1,9 @@
1
  ---
2
- language:
3
- - en
4
  license: apache-2.0
5
  tags:
6
- - audio
7
- - speech
8
- - wav2vec2
9
  - generated_from_trainer
 
 
10
  model-index:
11
  - name: torgo_xlsr_finetune_F03_keep_all
12
  results: []
@@ -17,7 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # torgo_xlsr_finetune_F03_keep_all
19
 
20
- This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the torgo dataset.
 
 
 
21
 
22
  ## Model description
23
 
@@ -47,6 +47,48 @@ The following hyperparameters were used during training:
47
  - lr_scheduler_warmup_steps: 1000
48
  - num_epochs: 20
49
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50
  ### Framework versions
51
 
52
  - Transformers 4.26.1
 
1
  ---
 
 
2
  license: apache-2.0
3
  tags:
 
 
 
4
  - generated_from_trainer
5
+ metrics:
6
+ - wer
7
  model-index:
8
  - name: torgo_xlsr_finetune_F03_keep_all
9
  results: []
 
14
 
15
  # torgo_xlsr_finetune_F03_keep_all
16
 
17
+ This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.1972
20
+ - Wer: 0.0443
21
 
22
  ## Model description
23
 
 
47
  - lr_scheduler_warmup_steps: 1000
48
  - num_epochs: 20
49
 
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
54
+ | 3.573 | 0.56 | 1000 | 3.3927 | 1.0 |
55
+ | 1.9872 | 1.11 | 2000 | 1.0729 | 0.7588 |
56
+ | 1.0338 | 1.67 | 3000 | 0.6272 | 0.4530 |
57
+ | 0.7363 | 2.22 | 4000 | 0.5054 | 0.3579 |
58
+ | 0.6181 | 2.78 | 5000 | 0.3583 | 0.2448 |
59
+ | 0.5327 | 3.33 | 6000 | 0.2902 | 0.1771 |
60
+ | 0.5046 | 3.89 | 7000 | 0.3202 | 0.1628 |
61
+ | 0.4227 | 4.44 | 8000 | 0.2460 | 0.1400 |
62
+ | 0.4405 | 5.0 | 9000 | 0.2750 | 0.1287 |
63
+ | 0.3927 | 5.55 | 10000 | 0.2235 | 0.0928 |
64
+ | 0.3496 | 6.11 | 11000 | 0.2621 | 0.1083 |
65
+ | 0.3294 | 6.66 | 12000 | 0.2056 | 0.0688 |
66
+ | 0.3201 | 7.22 | 13000 | 0.2155 | 0.0838 |
67
+ | 0.2973 | 7.77 | 14000 | 0.2909 | 0.0844 |
68
+ | 0.2758 | 8.33 | 15000 | 0.3096 | 0.0832 |
69
+ | 0.2688 | 8.88 | 16000 | 0.2420 | 0.0664 |
70
+ | 0.2537 | 9.44 | 17000 | 0.2438 | 0.0772 |
71
+ | 0.2642 | 9.99 | 18000 | 0.1836 | 0.0598 |
72
+ | 0.2611 | 10.55 | 19000 | 0.2562 | 0.0670 |
73
+ | 0.2019 | 11.1 | 20000 | 0.2084 | 0.0658 |
74
+ | 0.205 | 11.66 | 21000 | 0.1959 | 0.0628 |
75
+ | 0.2019 | 12.22 | 22000 | 0.2316 | 0.0700 |
76
+ | 0.1923 | 12.77 | 23000 | 0.2051 | 0.0664 |
77
+ | 0.1614 | 13.33 | 24000 | 0.2322 | 0.0724 |
78
+ | 0.1955 | 13.88 | 25000 | 0.1920 | 0.0551 |
79
+ | 0.1705 | 14.44 | 26000 | 0.2071 | 0.0521 |
80
+ | 0.1906 | 14.99 | 27000 | 0.2112 | 0.0533 |
81
+ | 0.1503 | 15.55 | 28000 | 0.1914 | 0.0491 |
82
+ | 0.1692 | 16.1 | 29000 | 0.1870 | 0.0557 |
83
+ | 0.149 | 16.66 | 30000 | 0.2172 | 0.0467 |
84
+ | 0.1413 | 17.21 | 31000 | 0.2313 | 0.0479 |
85
+ | 0.1466 | 17.77 | 32000 | 0.1989 | 0.0437 |
86
+ | 0.1533 | 18.32 | 33000 | 0.2078 | 0.0437 |
87
+ | 0.1176 | 18.88 | 34000 | 0.2034 | 0.0431 |
88
+ | 0.1189 | 19.43 | 35000 | 0.1929 | 0.0413 |
89
+ | 0.1056 | 19.99 | 36000 | 0.1972 | 0.0443 |
90
+
91
+
92
  ### Framework versions
93
 
94
  - Transformers 4.26.1