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
ae69f35
•
1 Parent(s): f4a8809

Model save

Browse files
Files changed (3) hide show
  1. README.md +29 -31
  2. model.safetensors +1 -1
  3. runs/May16_22-06-08_2e698a9c250f/events.out.tfevents.1715893684.2e698a9c250f.3535.0 +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: 0.4086
23
- - Wer: 0.3122
24
 
25
  ## Model description
26
 
@@ -55,32 +53,32 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Wer |
57
  |:-------------:|:------:|:----:|:---------------:|:------:|
58
- | No log | 0.1414 | 100 | 3.6264 | 1.0 |
59
- | No log | 0.2829 | 200 | 3.1080 | 1.0 |
60
- | No log | 0.4243 | 300 | 2.5440 | 0.9863 |
61
- | No log | 0.5658 | 400 | 1.2381 | 0.8110 |
62
- | 3.4586 | 0.7072 | 500 | 1.0036 | 0.7184 |
63
- | 3.4586 | 0.8487 | 600 | 0.8524 | 0.6379 |
64
- | 3.4586 | 0.9901 | 700 | 0.7411 | 0.5673 |
65
- | 3.4586 | 1.1315 | 800 | 0.6203 | 0.4838 |
66
- | 3.4586 | 1.2730 | 900 | 0.6017 | 0.4820 |
67
- | 0.8146 | 1.4144 | 1000 | 0.5637 | 0.4462 |
68
- | 0.8146 | 1.5559 | 1100 | 0.5381 | 0.4208 |
69
- | 0.8146 | 1.6973 | 1200 | 0.5155 | 0.4043 |
70
- | 0.8146 | 1.8388 | 1300 | 0.4858 | 0.3903 |
71
- | 0.8146 | 1.9802 | 1400 | 0.4758 | 0.3823 |
72
- | 0.6294 | 2.1216 | 1500 | 0.4604 | 0.3642 |
73
- | 0.6294 | 2.2631 | 1600 | 0.4531 | 0.3536 |
74
- | 0.6294 | 2.4045 | 1700 | 0.4435 | 0.3511 |
75
- | 0.6294 | 2.5460 | 1800 | 0.4366 | 0.3499 |
76
- | 0.6294 | 2.6874 | 1900 | 0.4309 | 0.3451 |
77
- | 0.4914 | 2.8289 | 2000 | 0.4252 | 0.3368 |
78
- | 0.4914 | 2.9703 | 2100 | 0.4218 | 0.3285 |
79
- | 0.4914 | 3.1117 | 2200 | 0.4208 | 0.3251 |
80
- | 0.4914 | 3.2532 | 2300 | 0.4144 | 0.3236 |
81
- | 0.4914 | 3.3946 | 2400 | 0.4140 | 0.3165 |
82
- | 0.4011 | 3.5361 | 2500 | 0.4133 | 0.3157 |
83
- | 0.4011 | 3.6775 | 2600 | 0.4086 | 0.3122 |
84
 
85
 
86
  ### 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: 0.4232
21
+ - Wer: 0.3216
22
 
23
  ## Model description
24
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:------:|:----:|:---------------:|:------:|
56
+ | No log | 0.1414 | 100 | 3.6050 | 1.0 |
57
+ | No log | 0.2829 | 200 | 2.9801 | 1.0 |
58
+ | No log | 0.4243 | 300 | 2.6344 | 0.9829 |
59
+ | No log | 0.5658 | 400 | 1.1876 | 0.8078 |
60
+ | 3.377 | 0.7072 | 500 | 1.0060 | 0.7694 |
61
+ | 3.377 | 0.8487 | 600 | 0.8394 | 0.6381 |
62
+ | 3.377 | 0.9901 | 700 | 0.7753 | 0.5871 |
63
+ | 3.377 | 1.1315 | 800 | 0.6411 | 0.4923 |
64
+ | 3.377 | 1.2730 | 900 | 0.6322 | 0.5023 |
65
+ | 0.8318 | 1.4144 | 1000 | 0.5858 | 0.4564 |
66
+ | 0.8318 | 1.5559 | 1100 | 0.5580 | 0.4334 |
67
+ | 0.8318 | 1.6973 | 1200 | 0.5396 | 0.4204 |
68
+ | 0.8318 | 1.8388 | 1300 | 0.5092 | 0.4033 |
69
+ | 0.8318 | 1.9802 | 1400 | 0.4942 | 0.3903 |
70
+ | 0.6486 | 2.1216 | 1500 | 0.4773 | 0.3778 |
71
+ | 0.6486 | 2.2631 | 1600 | 0.4728 | 0.3650 |
72
+ | 0.6486 | 2.4045 | 1700 | 0.4648 | 0.3623 |
73
+ | 0.6486 | 2.5460 | 1800 | 0.4559 | 0.3528 |
74
+ | 0.6486 | 2.6874 | 1900 | 0.4480 | 0.3527 |
75
+ | 0.5049 | 2.8289 | 2000 | 0.4383 | 0.3384 |
76
+ | 0.5049 | 2.9703 | 2100 | 0.4345 | 0.3355 |
77
+ | 0.5049 | 3.1117 | 2200 | 0.4345 | 0.3300 |
78
+ | 0.5049 | 3.2532 | 2300 | 0.4298 | 0.3272 |
79
+ | 0.5049 | 3.3946 | 2400 | 0.4292 | 0.3246 |
80
+ | 0.4131 | 3.5361 | 2500 | 0.4255 | 0.3232 |
81
+ | 0.4131 | 3.6775 | 2600 | 0.4232 | 0.3216 |
82
 
83
 
84
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f054f1571386a73baed8ec00614ac31a6e7bdcb94fee67410eeb9552c729ce8e
3
  size 1262012480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4644b32282a0bede644cd2ba0f5b4c28f04552d26162209de24cc3a7f25af765
3
  size 1262012480
runs/May16_22-06-08_2e698a9c250f/events.out.tfevents.1715893684.2e698a9c250f.3535.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9f223dd8883083d2a0f84b6e90271fcdf7084f3f578c5c2f7ef31067602b0cf
3
- size 14895
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15a70cb864fc985d9112a1ff7085db4e757a1ed3a6d3e9cc9da3c9b6f48357c9
3
+ size 16096