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
b9968c0
•
1 Parent(s): 410e142

Model save

Browse files
Files changed (3) hide show
  1. README.md +29 -31
  2. model.safetensors +1 -1
  3. runs/May27_10-13-44_5cce808c63ba/events.out.tfevents.1716802471.5cce808c63ba.31.0 +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: 0.4971
23
- - Wer: 0.3381
24
 
25
  ## Model description
26
 
@@ -53,32 +51,32 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:------:|:----:|:---------------:|:------:|
56
- | No log | 0.1548 | 100 | 3.5561 | 1.0 |
57
- | No log | 0.3096 | 200 | 3.3712 | 1.0 |
58
- | No log | 0.4644 | 300 | 3.1736 | 1.0 |
59
- | No log | 0.6192 | 400 | 1.1719 | 0.7910 |
60
- | 3.7217 | 0.7740 | 500 | 0.9169 | 0.6776 |
61
- | 3.7217 | 0.9288 | 600 | 0.8097 | 0.6191 |
62
- | 3.7217 | 1.0836 | 700 | 0.6986 | 0.5080 |
63
- | 3.7217 | 1.2384 | 800 | 0.6123 | 0.4629 |
64
- | 3.7217 | 1.3932 | 900 | 0.5815 | 0.4499 |
65
- | 0.6148 | 1.5480 | 1000 | 0.5666 | 0.4218 |
66
- | 0.6148 | 1.7028 | 1100 | 0.5285 | 0.4049 |
67
- | 0.6148 | 1.8576 | 1200 | 0.5309 | 0.3972 |
68
- | 0.6148 | 2.0124 | 1300 | 0.4993 | 0.3818 |
69
- | 0.6148 | 2.1672 | 1400 | 0.4779 | 0.3722 |
70
- | 0.4634 | 2.3220 | 1500 | 0.4679 | 0.3659 |
71
- | 0.4634 | 2.4768 | 1600 | 0.4679 | 0.3621 |
72
- | 0.4634 | 2.6316 | 1700 | 0.4525 | 0.3504 |
73
- | 0.4634 | 2.7864 | 1800 | 0.4353 | 0.3357 |
74
- | 0.4634 | 2.9412 | 1900 | 0.4358 | 0.3423 |
75
- | 0.3708 | 3.0960 | 2000 | 0.4391 | 0.3355 |
76
- | 0.3708 | 3.2508 | 2100 | 0.4307 | 0.3282 |
77
- | 0.3708 | 3.4056 | 2200 | 0.4274 | 0.3275 |
78
- | 0.3708 | 3.5604 | 2300 | 0.4388 | 0.3246 |
79
- | 0.3708 | 3.7152 | 2400 | 0.4521 | 0.3277 |
80
- | 0.3391 | 3.8700 | 2500 | 0.4861 | 0.3390 |
81
- | 0.3391 | 4.0248 | 2600 | 0.4971 | 0.3381 |
82
 
83
 
84
  ### 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: 0.4593
21
+ - Wer: 0.3553
22
 
23
  ## Model description
24
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:------:|:----:|:---------------:|:------:|
54
+ | No log | 0.0566 | 100 | 3.5994 | 1.0 |
55
+ | No log | 0.1133 | 200 | 3.0224 | 1.0 |
56
+ | No log | 0.1699 | 300 | 1.9627 | 0.9061 |
57
+ | No log | 0.2265 | 400 | 0.9921 | 0.6952 |
58
+ | 3.6184 | 0.2831 | 500 | 0.8504 | 0.6158 |
59
+ | 3.6184 | 0.3398 | 600 | 0.7936 | 0.5964 |
60
+ | 3.6184 | 0.3964 | 700 | 0.7601 | 0.5606 |
61
+ | 3.6184 | 0.4530 | 800 | 0.6909 | 0.5128 |
62
+ | 3.6184 | 0.5096 | 900 | 0.6617 | 0.4916 |
63
+ | 0.4662 | 0.5663 | 1000 | 0.6467 | 0.4812 |
64
+ | 0.4662 | 0.6229 | 1100 | 0.6144 | 0.4639 |
65
+ | 0.4662 | 0.6795 | 1200 | 0.5942 | 0.4537 |
66
+ | 0.4662 | 0.7361 | 1300 | 0.5675 | 0.4351 |
67
+ | 0.4662 | 0.7928 | 1400 | 0.5539 | 0.4230 |
68
+ | 0.3508 | 0.8494 | 1500 | 0.5448 | 0.4144 |
69
+ | 0.3508 | 0.9060 | 1600 | 0.5326 | 0.4066 |
70
+ | 0.3508 | 0.9626 | 1700 | 0.5155 | 0.3989 |
71
+ | 0.3508 | 1.0193 | 1800 | 0.5067 | 0.3856 |
72
+ | 0.3508 | 1.0759 | 1900 | 0.4916 | 0.3724 |
73
+ | 0.2774 | 1.1325 | 2000 | 0.4855 | 0.3697 |
74
+ | 0.2774 | 1.1891 | 2100 | 0.4798 | 0.3661 |
75
+ | 0.2774 | 1.2458 | 2200 | 0.4774 | 0.3646 |
76
+ | 0.2774 | 1.3024 | 2300 | 0.4699 | 0.3585 |
77
+ | 0.2774 | 1.3590 | 2400 | 0.4651 | 0.3550 |
78
+ | 0.2328 | 1.4156 | 2500 | 0.4611 | 0.3570 |
79
+ | 0.2328 | 1.4723 | 2600 | 0.4593 | 0.3553 |
80
 
81
 
82
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c5e7097e471ea95b7668a25bd925c89b4c0565dc91703238ffbb10e11c85131
3
  size 1261996080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb2bff4e51dfcec1d3b12b0be33670a4aedd72bac2661a541728dfecf4e4d083
3
  size 1261996080
runs/May27_10-13-44_5cce808c63ba/events.out.tfevents.1716802471.5cce808c63ba.31.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7482eb01b9601337338c41b2762b9bb66a8a778d18264394006bbcd30a7948b3
3
- size 14907
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b23d43f359e449579aceccf96306cd0e27a5db6fb7db2c38dd98656b88957cf6
3
+ size 16108