Hugging Face's logo

DewiBrynJones
/
wav2vec2-xlsr-53-ft-btb-cv-other-cy

Automatic Speech Recognition
TensorBoard
Safetensors
wav2vec2
./data-configs/btb-cv-other.json
Generated from Trainer
Model card Files Metrics Community
DewiBrynJones commited on
Commit
afd9ae6
•
1 Parent(s): bf877c4

Model save

Browse files
Files changed (1) hide show
  1. README.md +18 -20
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
- - ./data-configs/btb-cv-other.json
7
  - generated_from_trainer
8
  metrics:
9
  - wer
@@ -19,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  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.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.4934
23
- - Wer: 0.3776
24
 
25
  ## Model description
26
 
@@ -53,22 +51,22 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:------:|:----:|:---------------:|:------:|
56
- | 5.1054 | 0.0755 | 500 | 2.8161 | 1.0 |
57
- | 1.4196 | 0.1509 | 1000 | 1.1687 | 0.7941 |
58
- | 1.0028 | 0.2264 | 1500 | 0.9890 | 0.6953 |
59
- | 0.8942 | 0.3019 | 2000 | 0.8935 | 0.6195 |
60
- | 0.8285 | 0.3774 | 2500 | 0.8221 | 0.6075 |
61
- | 0.763 | 0.4528 | 3000 | 0.7165 | 0.5307 |
62
- | 0.7203 | 0.5283 | 3500 | 0.6892 | 0.5054 |
63
- | 0.7051 | 0.6038 | 4000 | 0.6848 | 0.5070 |
64
- | 0.6568 | 0.6792 | 4500 | 0.6342 | 0.4926 |
65
- | 0.6315 | 0.7547 | 5000 | 0.5956 | 0.4494 |
66
- | 0.6171 | 0.8302 | 5500 | 0.5533 | 0.4305 |
67
- | 0.5717 | 0.9057 | 6000 | 0.5360 | 0.4212 |
68
- | 0.5699 | 0.9811 | 6500 | 0.5184 | 0.4040 |
69
- | 0.4905 | 1.0566 | 7000 | 0.5081 | 0.3967 |
70
- | 0.4706 | 1.1321 | 7500 | 0.4991 | 0.3825 |
71
- | 0.4614 | 1.2075 | 8000 | 0.4934 | 0.3776 |
72
 
73
 
74
  ### 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
 
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: 0.3727
22
 
23
  ## Model description
24
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:------:|:----:|:---------------:|:------:|
54
+ | 4.9036 | 0.0643 | 500 | inf | 0.9912 |
55
+ | 1.3889 | 0.1286 | 1000 | inf | 0.7934 |
56
+ | 1.0207 | 0.1929 | 1500 | inf | 0.6829 |
57
+ | 0.8901 | 0.2572 | 2000 | inf | 0.6450 |
58
+ | 0.8467 | 0.3215 | 2500 | inf | 0.5458 |
59
+ | 0.7813 | 0.3859 | 3000 | inf | 0.5367 |
60
+ | 0.7456 | 0.4502 | 3500 | inf | 0.5156 |
61
+ | 0.7312 | 0.5145 | 4000 | inf | 0.4801 |
62
+ | 0.6929 | 0.5788 | 4500 | inf | 0.4659 |
63
+ | 0.6567 | 0.6431 | 5000 | inf | 0.4405 |
64
+ | 0.6413 | 0.7074 | 5500 | inf | 0.4199 |
65
+ | 0.6187 | 0.7717 | 6000 | inf | 0.4102 |
66
+ | 0.6086 | 0.8360 | 6500 | inf | 0.4037 |
67
+ | 0.585 | 0.9003 | 7000 | inf | 0.3872 |
68
+ | 0.5509 | 0.9646 | 7500 | inf | 0.3832 |
69
+ | 0.5263 | 1.0289 | 8000 | inf | 0.3727 |
70
 
71
 
72
  ### Framework versions