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
af4e86d
•
1 Parent(s): a480a37

Model save

Browse files
Files changed (1) hide show
  1. README.md +25 -37
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: nan
23
- - Wer: 1.0
24
 
25
  ## Model description
26
 
@@ -45,44 +43,34 @@ The following hyperparameters were used during training:
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
- - lr_scheduler_warmup_steps: 1500
49
- - training_steps: 15000
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:------:|:-----:|:---------------:|:------:|
56
- | 5.7778 | 0.0321 | 500 | 2.8852 | 1.0 |
57
- | 1.4914 | 0.0641 | 1000 | 1.2012 | 0.7806 |
58
- | 0.8803 | 0.0962 | 1500 | 1.1212 | 0.7590 |
59
- | 0.7723 | 0.1283 | 2000 | 0.9681 | 0.6770 |
60
- | 0.6988 | 0.1603 | 2500 | 0.9453 | 0.6599 |
61
- | 0.6392 | 0.1924 | 3000 | 0.8691 | 0.6200 |
62
- | 0.6114 | 0.2244 | 3500 | 0.8661 | 0.6192 |
63
- | 0.5807 | 0.2565 | 4000 | 0.7885 | 0.5794 |
64
- | 0.5534 | 0.2886 | 4500 | 0.7739 | 0.5490 |
65
- | 0.5358 | 0.3206 | 5000 | 0.7416 | 0.5415 |
66
- | 0.5189 | 0.3527 | 5500 | 0.7362 | 0.5303 |
67
- | 0.4991 | 0.3848 | 6000 | 0.7188 | 0.5066 |
68
- | 0.48 | 0.4168 | 6500 | 0.6985 | 0.5178 |
69
- | 0.463 | 0.4489 | 7000 | 0.6682 | 0.4933 |
70
- | 0.4477 | 0.4810 | 7500 | 0.6625 | 0.4867 |
71
- | 0.4431 | 0.5130 | 8000 | 0.6374 | 0.4736 |
72
- | 0.4392 | 0.5451 | 8500 | 0.6392 | 0.4772 |
73
- | 0.4197 | 0.5771 | 9000 | 0.6159 | 0.4547 |
74
- | 0.4147 | 0.6092 | 9500 | 0.5995 | 0.4522 |
75
- | 0.3912 | 0.6413 | 10000 | 0.5848 | 0.4286 |
76
- | 0.3742 | 0.6733 | 10500 | 0.5850 | 0.4259 |
77
- | 0.402 | 0.7054 | 11000 | 0.6352 | 0.4489 |
78
- | 0.5746 | 0.7375 | 11500 | 0.7712 | 0.5171 |
79
- | 0.5783 | 0.7695 | 12000 | nan | 1.0 |
80
- | 0.0 | 0.8016 | 12500 | nan | 1.0 |
81
- | 0.0 | 0.8337 | 13000 | nan | 1.0 |
82
- | 0.0 | 0.8657 | 13500 | nan | 1.0 |
83
- | 0.0 | 0.8978 | 14000 | nan | 1.0 |
84
- | 0.0 | 0.9298 | 14500 | nan | 1.0 |
85
- | 0.0 | 0.9619 | 15000 | nan | 1.0 |
86
 
87
 
88
  ### 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: 0.6832
21
+ - Wer: 0.4641
22
 
23
  ## Model description
24
 
 
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 1000
47
+ - training_steps: 10000
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:------:|:-----:|:---------------:|:------:|
54
+ | 4.8422 | 0.0854 | 500 | 2.2692 | 0.9886 |
55
+ | 1.2704 | 0.1709 | 1000 | 1.1623 | 0.7745 |
56
+ | 1.0177 | 0.2563 | 1500 | 0.9608 | 0.6586 |
57
+ | 0.9289 | 0.3417 | 2000 | 0.8117 | 0.6027 |
58
+ | 0.855 | 0.4271 | 2500 | 0.7981 | 0.5627 |
59
+ | 0.804 | 0.5126 | 3000 | 0.7293 | 0.5387 |
60
+ | 0.7384 | 0.5980 | 3500 | 0.6784 | 0.5150 |
61
+ | 0.7277 | 0.6834 | 4000 | 0.6553 | 0.4961 |
62
+ | 0.7009 | 0.7688 | 4500 | 0.6262 | 0.4684 |
63
+ | 0.6774 | 0.8543 | 5000 | 0.5955 | 0.4525 |
64
+ | 0.6427 | 0.9397 | 5500 | 0.5997 | 0.4741 |
65
+ | 0.6224 | 1.0251 | 6000 | 0.5653 | 0.4310 |
66
+ | 0.5507 | 1.1105 | 6500 | 0.5521 | 0.4173 |
67
+ | 0.6425 | 1.1960 | 7000 | 0.9010 | 0.5927 |
68
+ | 0.7218 | 1.2814 | 7500 | 0.7136 | 0.5011 |
69
+ | 0.8592 | 1.3668 | 8000 | 0.8863 | 0.6393 |
70
+ | 0.8668 | 1.4522 | 8500 | 0.7689 | 0.5330 |
71
+ | 0.7688 | 1.5377 | 9000 | 0.7101 | 0.4776 |
72
+ | 0.688 | 1.6231 | 9500 | 0.6742 | 0.4661 |
73
+ | 0.7079 | 1.7085 | 10000 | 0.6832 | 0.4641 |
 
 
 
 
 
 
 
 
 
 
74
 
75
 
76
  ### Framework versions