Hugging Face's logo

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

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
DewiBrynJones/banc-trawsgrifiadau-bangor-clean
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
DewiBrynJones commited on
Commit
d20d107
•
1 Parent(s): a5c8794

Model save

Browse files
Files changed (3) hide show
  1. README.md +30 -31
  2. model.safetensors +1 -1
  3. runs/May16_17-08-56_2e698a9c250f/events.out.tfevents.1715875744.2e698a9c250f.1150.0 +2 -2
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-normalized
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-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-NORMALIZED - DEFAULT dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.4589
23
- - Wer: 0.3743
24
 
25
  ## Model description
26
 
@@ -48,38 +46,39 @@ The following hyperparameters were used during training:
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
  - lr_scheduler_warmup_steps: 500
51
- - training_steps: 2500
52
  - mixed_precision_training: Native AMP
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Wer |
57
  |:-------------:|:------:|:----:|:---------------:|:------:|
58
- | No log | 0.1414 | 100 | 4.0354 | 1.0 |
59
- | No log | 0.2829 | 200 | 3.0977 | 1.0 |
60
- | No log | 0.4243 | 300 | 3.0769 | 1.0 |
61
- | No log | 0.5658 | 400 | 1.3738 | 0.8914 |
62
- | 3.7586 | 0.7072 | 500 | 1.0915 | 0.7692 |
63
- | 3.7586 | 0.8487 | 600 | 0.9361 | 0.6855 |
64
- | 3.7586 | 0.9901 | 700 | 0.8495 | 0.6247 |
65
- | 3.7586 | 1.1315 | 800 | 0.6886 | 0.5397 |
66
- | 3.7586 | 1.2730 | 900 | 0.6704 | 0.5312 |
67
- | 0.8877 | 1.4144 | 1000 | 0.6237 | 0.4950 |
68
- | 0.8877 | 1.5559 | 1100 | 0.5992 | 0.4768 |
69
- | 0.8877 | 1.6973 | 1200 | 0.5730 | 0.4522 |
70
- | 0.8877 | 1.8388 | 1300 | 0.5504 | 0.4418 |
71
- | 0.8877 | 1.9802 | 1400 | 0.5288 | 0.4259 |
72
- | 0.6844 | 2.1216 | 1500 | 0.5165 | 0.4217 |
73
- | 0.6844 | 2.2631 | 1600 | 0.5072 | 0.4193 |
74
- | 0.6844 | 2.4045 | 1700 | 0.4984 | 0.4155 |
75
- | 0.6844 | 2.5460 | 1800 | 0.4882 | 0.4097 |
76
- | 0.6844 | 2.6874 | 1900 | 0.4804 | 0.4080 |
77
- | 0.537 | 2.8289 | 2000 | 0.4700 | 0.3927 |
78
- | 0.537 | 2.9703 | 2100 | 0.4677 | 0.3885 |
79
- | 0.537 | 3.1117 | 2200 | 0.4683 | 0.3857 |
80
- | 0.537 | 3.2532 | 2300 | 0.4618 | 0.3792 |
81
- | 0.537 | 3.3946 | 2400 | 0.4604 | 0.3763 |
82
- | 0.4434 | 3.5361 | 2500 | 0.4589 | 0.3743 |
 
83
 
84
 
85
  ### 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-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: 0.4086
21
+ - Wer: 0.3122
22
 
23
  ## Model description
24
 
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 500
49
+ - training_steps: 2600
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:------:|:----:|:---------------:|:------:|
56
+ | No log | 0.1414 | 100 | 3.6264 | 1.0 |
57
+ | No log | 0.2829 | 200 | 3.1080 | 1.0 |
58
+ | No log | 0.4243 | 300 | 2.5440 | 0.9863 |
59
+ | No log | 0.5658 | 400 | 1.2381 | 0.8110 |
60
+ | 3.4586 | 0.7072 | 500 | 1.0036 | 0.7184 |
61
+ | 3.4586 | 0.8487 | 600 | 0.8524 | 0.6379 |
62
+ | 3.4586 | 0.9901 | 700 | 0.7411 | 0.5673 |
63
+ | 3.4586 | 1.1315 | 800 | 0.6203 | 0.4838 |
64
+ | 3.4586 | 1.2730 | 900 | 0.6017 | 0.4820 |
65
+ | 0.8146 | 1.4144 | 1000 | 0.5637 | 0.4462 |
66
+ | 0.8146 | 1.5559 | 1100 | 0.5381 | 0.4208 |
67
+ | 0.8146 | 1.6973 | 1200 | 0.5155 | 0.4043 |
68
+ | 0.8146 | 1.8388 | 1300 | 0.4858 | 0.3903 |
69
+ | 0.8146 | 1.9802 | 1400 | 0.4758 | 0.3823 |
70
+ | 0.6294 | 2.1216 | 1500 | 0.4604 | 0.3642 |
71
+ | 0.6294 | 2.2631 | 1600 | 0.4531 | 0.3536 |
72
+ | 0.6294 | 2.4045 | 1700 | 0.4435 | 0.3511 |
73
+ | 0.6294 | 2.5460 | 1800 | 0.4366 | 0.3499 |
74
+ | 0.6294 | 2.6874 | 1900 | 0.4309 | 0.3451 |
75
+ | 0.4914 | 2.8289 | 2000 | 0.4252 | 0.3368 |
76
+ | 0.4914 | 2.9703 | 2100 | 0.4218 | 0.3285 |
77
+ | 0.4914 | 3.1117 | 2200 | 0.4208 | 0.3251 |
78
+ | 0.4914 | 3.2532 | 2300 | 0.4144 | 0.3236 |
79
+ | 0.4914 | 3.3946 | 2400 | 0.4140 | 0.3165 |
80
+ | 0.4011 | 3.5361 | 2500 | 0.4133 | 0.3157 |
81
+ | 0.4011 | 3.6775 | 2600 | 0.4086 | 0.3122 |
82
 
83
 
84
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a780aa7dedb2fe4a87051ff8b6529e5f77b062854f58b8fc487b749b591b171a
3
  size 1262020680
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ab52e8e6c3ab3915a5498b8fb5609067f8d9905591911b1ed269ef177aeb6b9
3
  size 1262020680
runs/May16_17-08-56_2e698a9c250f/events.out.tfevents.1715875744.2e698a9c250f.1150.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:594bd8d7c95b5edaa8b8ddccd3d697a0a277b63ea1f3657c576784d3ffdb9279
3
- size 14895
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:832260cb2346c188d153108bf089784f4d0f93ab9808280062b4971dbbf1299d
3
+ size 16096