Hugging Face's logo

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

Automatic Speech Recognition
TensorBoard
Safetensors
wav2vec2
DewiBrynJones/banc-trawsgrifiadau-bangor-clean
Generated from Trainer
Model card Files Metrics Community
DewiBrynJones commited on
Commit
ac86de4
•
1 Parent(s): 2960c1c

Model save

Browse files
Files changed (1) hide show
  1. README.md +21 -14
README.md CHANGED
@@ -2,8 +2,6 @@
2
  license: apache-2.0
3
  base_model: DewiBrynJones/wav2vec2-xlsr-53-ft-btb-ccv-cy
4
  tags:
5
- - automatic-speech-recognition
6
- - DewiBrynJones/banc-trawsgrifiadau-bangor-clean
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-btb-ccv-ft-btb-cy
19
 
20
- This model is a fine-tuned version of [DewiBrynJones/wav2vec2-xlsr-53-ft-btb-ccv-cy](https://huggingface.co/DewiBrynJones/wav2vec2-xlsr-53-ft-btb-ccv-cy) on the DEWIBRYNJONES/BANC-TRAWSGRIFIADAU-BANGOR-CLEAN - DEFAULT dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.6272
23
- - Wer: 0.3870
24
 
25
  ## Model description
26
 
@@ -40,25 +38,34 @@ More information needed
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 0.0003
43
- - train_batch_size: 64
44
  - eval_batch_size: 64
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: 120
49
- - training_steps: 1200
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:------:|:----:|:---------------:|:------:|
56
- | No log | 0.4556 | 200 | 0.6623 | 0.4950 |
57
- | No log | 0.9112 | 400 | 0.5531 | 0.4115 |
58
- | 1.5958 | 1.3667 | 600 | 0.5107 | 0.3868 |
59
- | 1.5958 | 1.8223 | 800 | 0.5462 | 0.3999 |
60
- | 0.6374 | 2.2779 | 1000 | 0.5843 | 0.3879 |
61
- | 0.6374 | 2.7335 | 1200 | 0.6272 | 0.3870 |
 
 
 
 
 
 
 
 
 
62
 
63
 
64
  ### Framework versions
 
2
  license: apache-2.0
3
  base_model: DewiBrynJones/wav2vec2-xlsr-53-ft-btb-ccv-cy
4
  tags:
 
 
5
  - generated_from_trainer
6
  metrics:
7
  - wer
 
15
 
16
  # wav2vec2-btb-ccv-ft-btb-cy
17
 
18
+ This model is a fine-tuned version of [DewiBrynJones/wav2vec2-xlsr-53-ft-btb-ccv-cy](https://huggingface.co/DewiBrynJones/wav2vec2-xlsr-53-ft-btb-ccv-cy) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.4376
21
+ - Wer: 0.3395
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: 64
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: 300
47
+ - training_steps: 3000
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:------:|:----:|:---------------:|:------:|
54
+ | No log | 0.1139 | 200 | 0.7528 | 0.5049 |
55
+ | No log | 0.2278 | 400 | 0.6966 | 0.5050 |
56
+ | 2.117 | 0.3417 | 600 | 0.6128 | 0.4761 |
57
+ | 2.117 | 0.4556 | 800 | 0.6332 | 0.5017 |
58
+ | 0.7606 | 0.5695 | 1000 | 0.5895 | 0.4577 |
59
+ | 0.7606 | 0.6834 | 1200 | 0.5553 | 0.4211 |
60
+ | 0.7606 | 0.7973 | 1400 | 0.5304 | 0.4196 |
61
+ | 0.7049 | 0.9112 | 1600 | 0.5061 | 0.3873 |
62
+ | 0.7049 | 1.0251 | 1800 | 0.5090 | 0.3959 |
63
+ | 0.6136 | 1.1390 | 2000 | 0.4839 | 0.3758 |
64
+ | 0.6136 | 1.2528 | 2200 | 0.4692 | 0.3659 |
65
+ | 0.6136 | 1.3667 | 2400 | 0.4569 | 0.3544 |
66
+ | 0.5388 | 1.4806 | 2600 | 0.4488 | 0.3485 |
67
+ | 0.5388 | 1.5945 | 2800 | 0.4411 | 0.3423 |
68
+ | 0.5275 | 1.7084 | 3000 | 0.4376 | 0.3395 |
69
 
70
 
71
  ### Framework versions