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
ff51815
•
1 Parent(s): f60d64f

Model save

Browse files
Files changed (1) hide show
  1. README.md +33 -35
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: 0.3289
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: 16
44
  - eval_batch_size: 8
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -53,36 +51,36 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:------:|:----:|:---------------:|:------:|
56
- | No log | 0.0772 | 200 | inf | 1.0 |
57
- | No log | 0.1544 | 400 | inf | 0.9938 |
58
- | 3.9317 | 0.2317 | 600 | inf | 0.7576 |
59
- | 3.9317 | 0.3089 | 800 | inf | 0.6942 |
60
- | 0.9699 | 0.3861 | 1000 | inf | 0.5763 |
61
- | 0.9699 | 0.4633 | 1200 | inf | 0.5519 |
62
- | 0.9699 | 0.5405 | 1400 | inf | 0.5174 |
63
- | 0.8031 | 0.6178 | 1600 | inf | 0.5338 |
64
- | 0.8031 | 0.6950 | 1800 | inf | 0.4777 |
65
- | 0.7169 | 0.7722 | 2000 | inf | 0.4504 |
66
- | 0.7169 | 0.8494 | 2200 | inf | 0.4500 |
67
- | 0.7169 | 0.9266 | 2400 | inf | 0.4432 |
68
- | 0.6687 | 1.0039 | 2600 | inf | 0.4176 |
69
- | 0.6687 | 1.0811 | 2800 | inf | 0.4054 |
70
- | 0.5609 | 1.1583 | 3000 | inf | 0.4009 |
71
- | 0.5609 | 1.2355 | 3200 | inf | 0.4023 |
72
- | 0.5609 | 1.3127 | 3400 | inf | 0.3919 |
73
- | 0.5324 | 1.3900 | 3600 | inf | 0.3795 |
74
- | 0.5324 | 1.4672 | 3800 | inf | 0.3752 |
75
- | 0.5196 | 1.5444 | 4000 | inf | 0.3662 |
76
- | 0.5196 | 1.6216 | 4200 | inf | 0.3703 |
77
- | 0.5196 | 1.6988 | 4400 | inf | 0.3614 |
78
- | 0.4967 | 1.7761 | 4600 | inf | 0.3530 |
79
- | 0.4967 | 1.8533 | 4800 | inf | 0.3481 |
80
- | 0.4735 | 1.9305 | 5000 | inf | 0.3506 |
81
- | 0.4735 | 2.0077 | 5200 | inf | 0.3432 |
82
- | 0.4735 | 2.0849 | 5400 | inf | 0.3369 |
83
- | 0.4244 | 2.1622 | 5600 | inf | 0.3296 |
84
- | 0.4244 | 2.2394 | 5800 | inf | 0.3295 |
85
- | 0.3674 | 2.3166 | 6000 | inf | 0.3289 |
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: inf
21
+ - Wer: 0.5238
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 0.0003
41
+ - train_batch_size: 32
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 | 0.1544 | 200 | inf | 1.0 |
55
+ | No log | 0.3089 | 400 | inf | 0.8661 |
56
+ | 3.7305 | 0.4633 | 600 | inf | 0.7040 |
57
+ | 3.7305 | 0.6178 | 800 | inf | 0.5506 |
58
+ | 0.8464 | 0.7722 | 1000 | inf | 0.5168 |
59
+ | 0.8464 | 0.9266 | 1200 | inf | 0.4825 |
60
+ | 0.8464 | 1.0811 | 1400 | inf | 0.4601 |
61
+ | 0.6629 | 1.2355 | 1600 | inf | 0.4445 |
62
+ | 0.6629 | 1.3900 | 1800 | inf | 0.4143 |
63
+ | 0.5655 | 1.5444 | 2000 | inf | 0.4170 |
64
+ | 0.5655 | 1.6988 | 2200 | inf | 0.4047 |
65
+ | 0.5655 | 1.8533 | 2400 | inf | 0.3966 |
66
+ | 0.5524 | 2.0077 | 2600 | inf | 0.3779 |
67
+ | 0.5524 | 2.1622 | 2800 | inf | 0.3737 |
68
+ | 0.4773 | 2.3166 | 3000 | inf | 0.3698 |
69
+ | 0.4773 | 2.4710 | 3200 | inf | 0.3724 |
70
+ | 0.4773 | 2.6255 | 3400 | inf | 0.3584 |
71
+ | 0.4694 | 2.7799 | 3600 | inf | 0.3821 |
72
+ | 0.4694 | 2.9344 | 3800 | inf | 0.4730 |
73
+ | 0.6537 | 3.0888 | 4000 | inf | 0.4754 |
74
+ | 0.6537 | 3.2432 | 4200 | inf | 0.5899 |
75
+ | 0.6537 | 3.3977 | 4400 | inf | 0.5958 |
76
+ | 0.8238 | 3.5521 | 4600 | inf | 0.6336 |
77
+ | 0.8238 | 3.7066 | 4800 | inf | 0.6026 |
78
+ | 0.8682 | 3.8610 | 5000 | inf | 0.5671 |
79
+ | 0.8682 | 4.0154 | 5200 | inf | 0.5378 |
80
+ | 0.8682 | 4.1699 | 5400 | inf | 0.5374 |
81
+ | 0.855 | 4.3243 | 5600 | inf | 0.5328 |
82
+ | 0.855 | 4.4788 | 5800 | inf | 0.5225 |
83
+ | 0.9644 | 4.6332 | 6000 | inf | 0.5238 |
84
 
85
 
86
  ### Framework versions