DewiBrynJones commited on
Commit
ade44d2
1 Parent(s): 721256e

Model save

Browse files
Files changed (1) hide show
  1. README.md +23 -25
README.md CHANGED
@@ -2,8 +2,6 @@
2
  license: apache-2.0
3
  base_model: facebook/wav2vec2-large-xlsr-53
4
  tags:
5
- - automatic-speech-recognition
6
- - DewiBrynJones/banc-trawsgrifiadau-bangor-clean-with-ccv
7
  - generated_from_trainer
8
  metrics:
9
  - wer
@@ -17,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # wav2vec2-xlsr-53-ft-btb-ccv-cy
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 DEWIBRYNJONES/BANC-TRAWSGRIFIADAU-BANGOR-CLEAN-WITH-CCV - DEFAULT dataset.
21
  It achieves the following results on the evaluation set:
22
  - Loss: inf
23
- - Wer: 0.3352
24
 
25
  ## Model description
26
 
@@ -40,7 +38,7 @@ More information needed
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 0.0003
43
- - train_batch_size: 32
44
  - eval_batch_size: 8
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -53,26 +51,26 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:------:|:----:|:---------------:|:------:|
56
- | No log | 0.1544 | 200 | inf | 1.0 |
57
- | No log | 0.3089 | 400 | inf | 0.8237 |
58
- | 3.6679 | 0.4633 | 600 | inf | 0.7189 |
59
- | 3.6679 | 0.6178 | 800 | inf | 0.5541 |
60
- | 0.8341 | 0.7722 | 1000 | inf | 0.5124 |
61
- | 0.8341 | 0.9266 | 1200 | inf | 0.4895 |
62
- | 0.8341 | 1.0811 | 1400 | inf | 0.4527 |
63
- | 0.6524 | 1.2355 | 1600 | inf | 0.4340 |
64
- | 0.6524 | 1.3900 | 1800 | inf | 0.4071 |
65
- | 0.5566 | 1.5444 | 2000 | inf | 0.3942 |
66
- | 0.5566 | 1.6988 | 2200 | inf | 0.3907 |
67
- | 0.5566 | 1.8533 | 2400 | inf | 0.3778 |
68
- | 0.5324 | 2.0077 | 2600 | inf | 0.3624 |
69
- | 0.5324 | 2.1622 | 2800 | inf | 0.3534 |
70
- | 0.4444 | 2.3166 | 3000 | inf | 0.3496 |
71
- | 0.4444 | 2.4710 | 3200 | inf | 0.3416 |
72
- | 0.4444 | 2.6255 | 3400 | inf | 0.3407 |
73
- | 0.4254 | 2.7799 | 3600 | inf | 0.3346 |
74
- | 0.4254 | 2.9344 | 3800 | inf | 0.3378 |
75
- | 0.4273 | 3.0888 | 4000 | inf | 0.3352 |
76
 
77
 
78
  ### Framework versions
 
2
  license: apache-2.0
3
  base_model: facebook/wav2vec2-large-xlsr-53
4
  tags:
 
 
5
  - generated_from_trainer
6
  metrics:
7
  - wer
 
15
 
16
  # wav2vec2-xlsr-53-ft-btb-ccv-cy
17
 
18
+ This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: inf
21
+ - Wer: 0.3501
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 0.0003
41
+ - train_batch_size: 16
42
  - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:------:|:----:|:---------------:|:------:|
54
+ | No log | 0.0772 | 200 | inf | 1.0 |
55
+ | No log | 0.1544 | 400 | inf | 0.9262 |
56
+ | 3.9094 | 0.2317 | 600 | inf | 0.7767 |
57
+ | 3.9094 | 0.3089 | 800 | inf | 0.7365 |
58
+ | 0.9885 | 0.3861 | 1000 | inf | 0.6105 |
59
+ | 0.9885 | 0.4633 | 1200 | inf | 0.5431 |
60
+ | 0.9885 | 0.5405 | 1400 | inf | 0.5145 |
61
+ | 0.7974 | 0.6178 | 1600 | inf | 0.5231 |
62
+ | 0.7974 | 0.6950 | 1800 | inf | 0.4621 |
63
+ | 0.7068 | 0.7722 | 2000 | inf | 0.4532 |
64
+ | 0.7068 | 0.8494 | 2200 | inf | 0.4404 |
65
+ | 0.7068 | 0.9266 | 2400 | inf | 0.4195 |
66
+ | 0.6447 | 1.0039 | 2600 | inf | 0.4116 |
67
+ | 0.6447 | 1.0811 | 2800 | inf | 0.3890 |
68
+ | 0.5318 | 1.1583 | 3000 | inf | 0.3804 |
69
+ | 0.5318 | 1.2355 | 3200 | inf | 0.3734 |
70
+ | 0.5318 | 1.3127 | 3400 | inf | 0.3675 |
71
+ | 0.494 | 1.3900 | 3600 | inf | 0.3590 |
72
+ | 0.494 | 1.4672 | 3800 | inf | 0.3535 |
73
+ | 0.4794 | 1.5444 | 4000 | inf | 0.3501 |
74
 
75
 
76
  ### Framework versions