Hugging Face's logo

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

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
DewiBrynJones/banc-trawsgrifiadau-bangor-clean-with-ccv
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
DewiBrynJones commited on
Commit
8982e3e
•
1 Parent(s): 3947b25

Model save

Browse files
Files changed (3) hide show
  1. README.md +30 -34
  2. model.safetensors +1 -1
  3. runs/May23_22-05-49_7571a1a6d5fc/events.out.tfevents.1716498357.7571a1a6d5fc.916.0 +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-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: 0.4349
23
- - Wer: 0.3391
24
 
25
  ## Model description
26
 
@@ -40,11 +38,9 @@ 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
- - gradient_accumulation_steps: 2
47
- - total_train_batch_size: 32
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
  - lr_scheduler_warmup_steps: 500
@@ -55,32 +51,32 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Wer |
57
  |:-------------:|:------:|:----:|:---------------:|:------:|
58
- | No log | 0.0774 | 100 | 3.5346 | 1.0 |
59
- | No log | 0.1549 | 200 | 2.9829 | 1.0 |
60
- | No log | 0.2323 | 300 | 2.7705 | 1.0 |
61
- | No log | 0.3097 | 400 | 1.3696 | 0.8535 |
62
- | 3.7305 | 0.3871 | 500 | 1.0936 | 0.7465 |
63
- | 3.7305 | 0.4646 | 600 | 0.8457 | 0.6413 |
64
- | 3.7305 | 0.5420 | 700 | 0.7860 | 0.5836 |
65
- | 3.7305 | 0.6194 | 800 | 0.7366 | 0.5637 |
66
- | 3.7305 | 0.6969 | 900 | 0.7319 | 0.5494 |
67
- | 0.7504 | 0.7743 | 1000 | 0.6439 | 0.5104 |
68
- | 0.7504 | 0.8517 | 1100 | 0.6214 | 0.4759 |
69
- | 0.7504 | 0.9292 | 1200 | 0.5957 | 0.4628 |
70
- | 0.7504 | 1.0066 | 1300 | 0.5717 | 0.4353 |
71
- | 0.7504 | 1.0840 | 1400 | 0.5500 | 0.4192 |
72
- | 0.5571 | 1.1614 | 1500 | 0.5342 | 0.4073 |
73
- | 0.5571 | 1.2389 | 1600 | 0.5207 | 0.4024 |
74
- | 0.5571 | 1.3163 | 1700 | 0.5142 | 0.3969 |
75
- | 0.5571 | 1.3937 | 1800 | 0.5083 | 0.3958 |
76
- | 0.5571 | 1.4712 | 1900 | 0.4886 | 0.3825 |
77
- | 0.4603 | 1.5486 | 2000 | 0.4733 | 0.3743 |
78
- | 0.4603 | 1.6260 | 2100 | 0.4616 | 0.3619 |
79
- | 0.4603 | 1.7034 | 2200 | 0.4536 | 0.3627 |
80
- | 0.4603 | 1.7809 | 2300 | 0.4488 | 0.3487 |
81
- | 0.4603 | 1.8583 | 2400 | 0.4429 | 0.3481 |
82
- | 0.4163 | 1.9357 | 2500 | 0.4377 | 0.3419 |
83
- | 0.4163 | 2.0132 | 2600 | 0.4349 | 0.3391 |
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-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: 0.4971
21
+ - Wer: 0.3381
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 0.0003
41
+ - train_batch_size: 64
42
  - eval_batch_size: 8
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: 500
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:------:|:----:|:---------------:|:------:|
54
+ | No log | 0.1548 | 100 | 3.5561 | 1.0 |
55
+ | No log | 0.3096 | 200 | 3.3712 | 1.0 |
56
+ | No log | 0.4644 | 300 | 3.1736 | 1.0 |
57
+ | No log | 0.6192 | 400 | 1.1719 | 0.7910 |
58
+ | 3.7217 | 0.7740 | 500 | 0.9169 | 0.6776 |
59
+ | 3.7217 | 0.9288 | 600 | 0.8097 | 0.6191 |
60
+ | 3.7217 | 1.0836 | 700 | 0.6986 | 0.5080 |
61
+ | 3.7217 | 1.2384 | 800 | 0.6123 | 0.4629 |
62
+ | 3.7217 | 1.3932 | 900 | 0.5815 | 0.4499 |
63
+ | 0.6148 | 1.5480 | 1000 | 0.5666 | 0.4218 |
64
+ | 0.6148 | 1.7028 | 1100 | 0.5285 | 0.4049 |
65
+ | 0.6148 | 1.8576 | 1200 | 0.5309 | 0.3972 |
66
+ | 0.6148 | 2.0124 | 1300 | 0.4993 | 0.3818 |
67
+ | 0.6148 | 2.1672 | 1400 | 0.4779 | 0.3722 |
68
+ | 0.4634 | 2.3220 | 1500 | 0.4679 | 0.3659 |
69
+ | 0.4634 | 2.4768 | 1600 | 0.4679 | 0.3621 |
70
+ | 0.4634 | 2.6316 | 1700 | 0.4525 | 0.3504 |
71
+ | 0.4634 | 2.7864 | 1800 | 0.4353 | 0.3357 |
72
+ | 0.4634 | 2.9412 | 1900 | 0.4358 | 0.3423 |
73
+ | 0.3708 | 3.0960 | 2000 | 0.4391 | 0.3355 |
74
+ | 0.3708 | 3.2508 | 2100 | 0.4307 | 0.3282 |
75
+ | 0.3708 | 3.4056 | 2200 | 0.4274 | 0.3275 |
76
+ | 0.3708 | 3.5604 | 2300 | 0.4388 | 0.3246 |
77
+ | 0.3708 | 3.7152 | 2400 | 0.4521 | 0.3277 |
78
+ | 0.3391 | 3.8700 | 2500 | 0.4861 | 0.3390 |
79
+ | 0.3391 | 4.0248 | 2600 | 0.4971 | 0.3381 |
80
 
81
 
82
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75db3617a527eb0ee4de0e7909677c380de3ff4fc8ce84aa93309c25af9d4469
3
  size 1261996080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd020194e0e7ce2a5a62e5aae3e12d84fa0e86e909ef3791385fe0ca69b1d006
3
  size 1261996080
runs/May23_22-05-49_7571a1a6d5fc/events.out.tfevents.1716498357.7571a1a6d5fc.916.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18ec7654c02b6b559075297dc41943d0adb6fc897c717ab9007e9201d5f5c5d5
3
- size 14907
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e927624d3f39051d1c0b515c22343e12d55f290811e7ee34c04a5681047a8557
3
+ size 16108