Hugging Face's logo

DewiBrynJones
/
wav2vec2-xlsr-53-ft-btb-ccv-cy

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
DewiBrynJones commited on
Commit
3528274
•
1 Parent(s): 049efb2

Model save

Browse files
Files changed (1) hide show
  1. README.md +34 -26
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: 0.5324
23
- - Wer: 0.4014
24
 
25
  ## Model description
26
 
@@ -46,33 +44,43 @@ The following hyperparameters were used during training:
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 600
49
- - training_steps: 10000
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:------:|:-----:|:---------------:|:------:|
56
- | 4.7051 | 0.0321 | 500 | 1.7504 | 0.9570 |
57
- | 1.0409 | 0.0641 | 1000 | 1.1511 | 0.7761 |
58
- | 0.8183 | 0.0962 | 1500 | 1.0506 | 0.7097 |
59
- | 0.7091 | 0.1283 | 2000 | 0.9421 | 0.6610 |
60
- | 0.6547 | 0.1603 | 2500 | 0.8726 | 0.6128 |
61
- | 0.6088 | 0.1924 | 3000 | 0.8246 | 0.5990 |
62
- | 0.5781 | 0.2244 | 3500 | 0.8025 | 0.5747 |
63
- | 0.5429 | 0.2565 | 4000 | 0.7360 | 0.5305 |
64
- | 0.5104 | 0.2886 | 4500 | 0.7335 | 0.5394 |
65
- | 0.501 | 0.3206 | 5000 | 0.6933 | 0.5088 |
66
- | 0.4708 | 0.3527 | 5500 | 0.6770 | 0.5113 |
67
- | 0.4526 | 0.3848 | 6000 | 0.6609 | 0.4806 |
68
- | 0.4235 | 0.4168 | 6500 | 0.6373 | 0.4858 |
69
- | 0.4032 | 0.4489 | 7000 | 0.6048 | 0.4466 |
70
- | 0.3863 | 0.4810 | 7500 | 0.5946 | 0.4432 |
71
- | 0.3766 | 0.5130 | 8000 | 0.5737 | 0.4298 |
72
- | 0.3746 | 0.5451 | 8500 | 0.5668 | 0.4248 |
73
- | 0.3586 | 0.5771 | 9000 | 0.5485 | 0.4101 |
74
- | 0.3552 | 0.6092 | 9500 | 0.5378 | 0.4032 |
75
- | 0.3326 | 0.6413 | 10000 | 0.5324 | 0.4014 |
 
 
 
 
 
 
 
 
 
 
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: nan
21
+ - Wer: 1.0
22
 
23
  ## Model description
24
 
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 600
47
+ - training_steps: 15000
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:------:|:-----:|:---------------:|:------:|
54
+ | 4.6156 | 0.0321 | 500 | 1.5867 | 0.9177 |
55
+ | 1.0315 | 0.0641 | 1000 | 1.1748 | 0.7888 |
56
+ | 0.834 | 0.0962 | 1500 | 1.0393 | 0.7220 |
57
+ | 0.7184 | 0.1283 | 2000 | 0.9616 | 0.6637 |
58
+ | 0.6655 | 0.1603 | 2500 | 0.9034 | 0.6331 |
59
+ | 0.6193 | 0.1924 | 3000 | 0.8615 | 0.6239 |
60
+ | 0.5952 | 0.2244 | 3500 | 0.8161 | 0.5866 |
61
+ | 0.5622 | 0.2565 | 4000 | 0.8110 | 0.5851 |
62
+ | 0.5341 | 0.2886 | 4500 | 0.7580 | 0.5547 |
63
+ | 0.522 | 0.3206 | 5000 | 0.7397 | 0.5412 |
64
+ | 0.5123 | 0.3527 | 5500 | 0.7229 | 0.5317 |
65
+ | 0.4884 | 0.3848 | 6000 | 0.7235 | 0.5165 |
66
+ | 0.4658 | 0.4168 | 6500 | 0.6814 | 0.5117 |
67
+ | 0.4471 | 0.4489 | 7000 | 0.6623 | 0.4891 |
68
+ | 0.4338 | 0.4810 | 7500 | 0.6450 | 0.4914 |
69
+ | 0.4267 | 0.5130 | 8000 | 0.6256 | 0.4685 |
70
+ | 0.4283 | 0.5451 | 8500 | 0.6343 | 0.4711 |
71
+ | 0.4131 | 0.5771 | 9000 | 0.5989 | 0.4487 |
72
+ | 0.4317 | 0.6092 | 9500 | 0.7168 | 0.4920 |
73
+ | 0.5904 | 0.6413 | 10000 | nan | 0.7310 |
74
+ | 0.0513 | 0.6733 | 10500 | nan | 1.0 |
75
+ | 0.0 | 0.7054 | 11000 | nan | 1.0 |
76
+ | 0.0 | 0.7375 | 11500 | nan | 1.0 |
77
+ | 0.0 | 0.7695 | 12000 | nan | 1.0 |
78
+ | 0.0 | 0.8016 | 12500 | nan | 1.0 |
79
+ | 0.0 | 0.8337 | 13000 | nan | 1.0 |
80
+ | 0.0 | 0.8657 | 13500 | nan | 1.0 |
81
+ | 0.0 | 0.8978 | 14000 | nan | 1.0 |
82
+ | 0.0 | 0.9298 | 14500 | nan | 1.0 |
83
+ | 0.0 | 0.9619 | 15000 | nan | 1.0 |
84
 
85
 
86
  ### Framework versions