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
38874e9
•
1 Parent(s): ed306c0

Model save

Browse files
Files changed (1) hide show
  1. README.md +24 -56
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: 1.6956
23
- - Wer: 0.7702
24
 
25
  ## Model description
26
 
@@ -46,63 +44,33 @@ 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: 500
49
- - training_steps: 5000
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:------:|:----:|:---------------:|:------:|
56
- | No log | 0.1548 | 100 | 3.5587 | 1.0 |
57
- | No log | 0.3096 | 200 | 3.2506 | 1.0 |
58
- | No log | 0.4644 | 300 | 2.7740 | 1.0000 |
59
- | No log | 0.6192 | 400 | 1.1196 | 0.7807 |
60
- | 3.6484 | 0.7740 | 500 | 0.9134 | 0.6539 |
61
- | 3.6484 | 0.9288 | 600 | 0.7675 | 0.5923 |
62
- | 3.6484 | 1.0836 | 700 | 0.7208 | 0.5290 |
63
- | 3.6484 | 1.2384 | 800 | 0.6209 | 0.4745 |
64
- | 3.6484 | 1.3932 | 900 | 0.6220 | 0.4788 |
65
- | 0.6286 | 1.5480 | 1000 | 0.5739 | 0.4588 |
66
- | 0.6286 | 1.7028 | 1100 | 0.5642 | 0.4262 |
67
- | 0.6286 | 1.8576 | 1200 | 0.5512 | 0.4208 |
68
- | 0.6286 | 2.0124 | 1300 | 0.5275 | 0.3865 |
69
- | 0.6286 | 2.1672 | 1400 | 0.4955 | 0.3755 |
70
- | 0.4816 | 2.3220 | 1500 | 0.4909 | 0.3733 |
71
- | 0.4816 | 2.4768 | 1600 | 0.4983 | 0.3728 |
72
- | 0.4816 | 2.6316 | 1700 | 0.4891 | 0.3655 |
73
- | 0.4816 | 2.7864 | 1800 | 0.4796 | 0.3571 |
74
- | 0.4816 | 2.9412 | 1900 | 0.4643 | 0.3592 |
75
- | 0.4017 | 3.0960 | 2000 | 0.5085 | 0.3698 |
76
- | 0.4017 | 3.2508 | 2100 | 0.6755 | 0.4530 |
77
- | 0.4017 | 3.4056 | 2200 | 0.7100 | 0.5108 |
78
- | 0.4017 | 3.5604 | 2300 | 0.8311 | 0.5643 |
79
- | 0.4017 | 3.7152 | 2400 | 0.7032 | 0.5029 |
80
- | 0.6839 | 3.8700 | 2500 | 0.7071 | 0.5007 |
81
- | 0.6839 | 4.0248 | 2600 | 0.8224 | 0.5069 |
82
- | 0.6839 | 4.1796 | 2700 | 0.8344 | 0.5162 |
83
- | 0.6839 | 4.3344 | 2800 | 0.9089 | 0.5620 |
84
- | 0.6839 | 4.4892 | 2900 | 0.9665 | 0.5640 |
85
- | 0.8292 | 4.6440 | 3000 | 0.9128 | 0.5415 |
86
- | 0.8292 | 4.7988 | 3100 | 1.1925 | 0.5939 |
87
- | 0.8292 | 4.9536 | 3200 | 1.4327 | 0.6999 |
88
- | 0.8292 | 5.1084 | 3300 | 1.2741 | 0.7827 |
89
- | 0.8292 | 5.2632 | 3400 | 1.9348 | 0.8742 |
90
- | 1.4131 | 5.4180 | 3500 | 1.9216 | 0.9870 |
91
- | 1.4131 | 5.5728 | 3600 | 1.8565 | 0.9367 |
92
- | 1.4131 | 5.7276 | 3700 | 1.7828 | 0.8240 |
93
- | 1.4131 | 5.8824 | 3800 | 1.6847 | 0.8059 |
94
- | 1.4131 | 6.0372 | 3900 | 1.6440 | 0.7984 |
95
- | 1.7728 | 6.1920 | 4000 | 1.6765 | 0.8053 |
96
- | 1.7728 | 6.3467 | 4100 | 1.6733 | 0.8024 |
97
- | 1.7728 | 6.5015 | 4200 | 1.6601 | 0.7900 |
98
- | 1.7728 | 6.6563 | 4300 | 1.6605 | 0.7973 |
99
- | 1.7728 | 6.8111 | 4400 | 1.6599 | 0.7805 |
100
- | 1.6777 | 6.9659 | 4500 | 1.6359 | 0.7693 |
101
- | 1.6777 | 7.1207 | 4600 | 1.6400 | 0.7651 |
102
- | 1.6777 | 7.2755 | 4700 | 1.6759 | 0.7672 |
103
- | 1.6777 | 7.4303 | 4800 | 1.6849 | 0.7686 |
104
- | 1.6777 | 7.5851 | 4900 | 1.6858 | 0.7690 |
105
- | 1.683 | 7.7399 | 5000 | 1.6956 | 0.7702 |
106
 
107
 
108
  ### 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: 0.4200
21
+ - Wer: 0.3227
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: 500
47
+ - training_steps: 2000
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:------:|:----:|:---------------:|:------:|
54
+ | No log | 0.1548 | 100 | 3.5623 | 1.0 |
55
+ | No log | 0.3096 | 200 | 3.2967 | 1.0 |
56
+ | No log | 0.4644 | 300 | 2.6484 | 1.0000 |
57
+ | No log | 0.6192 | 400 | 1.0602 | 0.7315 |
58
+ | 3.6398 | 0.7740 | 500 | 0.8942 | 0.6696 |
59
+ | 3.6398 | 0.9288 | 600 | 0.7116 | 0.5361 |
60
+ | 3.6398 | 1.0836 | 700 | 0.6648 | 0.5101 |
61
+ | 3.6398 | 1.2384 | 800 | 0.5869 | 0.4528 |
62
+ | 3.6398 | 1.3932 | 900 | 0.5698 | 0.4359 |
63
+ | 0.5976 | 1.5480 | 1000 | 0.5408 | 0.4112 |
64
+ | 0.5976 | 1.7028 | 1100 | 0.5229 | 0.4196 |
65
+ | 0.5976 | 1.8576 | 1200 | 0.5055 | 0.3955 |
66
+ | 0.5976 | 2.0124 | 1300 | 0.4808 | 0.3709 |
67
+ | 0.5976 | 2.1672 | 1400 | 0.4667 | 0.3580 |
68
+ | 0.443 | 2.3220 | 1500 | 0.4573 | 0.3582 |
69
+ | 0.443 | 2.4768 | 1600 | 0.4475 | 0.3452 |
70
+ | 0.443 | 2.6316 | 1700 | 0.4369 | 0.3478 |
71
+ | 0.443 | 2.7864 | 1800 | 0.4227 | 0.3298 |
72
+ | 0.443 | 2.9412 | 1900 | 0.4169 | 0.3271 |
73
+ | 0.3475 | 3.0960 | 2000 | 0.4200 | 0.3227 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
74
 
75
 
76
  ### Framework versions