Hugging Face's logo

techiaith
/
wav2vec2-xlsr-53-ft-cy-en-withlm

Automatic Speech Recognition
Transformers
Safetensors
Welsh
English
wav2vec2
Inference Endpoints
Model card Files Community
DewiBrynJones commited on
Commit
124ec62
•
1 Parent(s): 7d9f705

Model save

Browse files
Files changed (1) hide show
  1. README.md +20 -22
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
- - techiaith/commonvoice_16_1_en_cy
7
  - generated_from_trainer
8
  metrics:
9
  - wer
@@ -17,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # wav2vec2-xlsr-53-ft-ccv-en-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 TECHIAITH/COMMONVOICE_16_1_EN_CY - DEFAULT dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.2765
23
  - Wer: 0.2115
24
 
25
  ## Model description
@@ -55,24 +53,24 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Wer |
57
  |:-------------:|:-----:|:----:|:---------------:|:------:|
58
- | 5.9898 | 0.25 | 500 | 1.3093 | 0.7971 |
59
- | 1.0749 | 0.5 | 1000 | 0.5816 | 0.4617 |
60
- | 0.4332 | 0.75 | 1500 | 0.4834 | 0.4091 |
61
- | 0.3303 | 1.01 | 2000 | 0.4203 | 0.3419 |
62
- | 0.276 | 1.26 | 2500 | 0.3910 | 0.3186 |
63
- | 0.2591 | 1.51 | 3000 | 0.3901 | 0.3067 |
64
- | 0.2501 | 1.76 | 3500 | 0.3646 | 0.2895 |
65
- | 0.224 | 2.01 | 4000 | 0.3517 | 0.2806 |
66
- | 0.182 | 2.26 | 4500 | 0.3348 | 0.2656 |
67
- | 0.1777 | 2.51 | 5000 | 0.3277 | 0.2612 |
68
- | 0.1734 | 2.77 | 5500 | 0.3323 | 0.2643 |
69
- | 0.1629 | 3.02 | 6000 | 0.3171 | 0.2485 |
70
- | 0.1338 | 3.27 | 6500 | 0.3103 | 0.2398 |
71
- | 0.1292 | 3.52 | 7000 | 0.2934 | 0.2268 |
72
- | 0.1264 | 3.77 | 7500 | 0.2923 | 0.2248 |
73
- | 0.118 | 4.02 | 8000 | 0.2880 | 0.2193 |
74
- | 0.0996 | 4.27 | 8500 | 0.2793 | 0.2124 |
75
- | 0.0969 | 4.52 | 9000 | 0.2765 | 0.2115 |
76
 
77
 
78
  ### 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-ccv-en-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: 0.2754
21
  - Wer: 0.2115
22
 
23
  ## Model description
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:-----:|:----:|:---------------:|:------:|
56
+ | 6.0574 | 0.25 | 500 | 2.0297 | 0.9991 |
57
+ | 1.224 | 0.5 | 1000 | 0.5368 | 0.4342 |
58
+ | 0.434 | 0.75 | 1500 | 0.4861 | 0.3891 |
59
+ | 0.3295 | 1.01 | 2000 | 0.4301 | 0.3411 |
60
+ | 0.2739 | 1.26 | 2500 | 0.3818 | 0.3053 |
61
+ | 0.2619 | 1.51 | 3000 | 0.3894 | 0.3060 |
62
+ | 0.2517 | 1.76 | 3500 | 0.3497 | 0.2802 |
63
+ | 0.2244 | 2.01 | 4000 | 0.3519 | 0.2792 |
64
+ | 0.1854 | 2.26 | 4500 | 0.3376 | 0.2718 |
65
+ | 0.1779 | 2.51 | 5000 | 0.3206 | 0.2520 |
66
+ | 0.1749 | 2.77 | 5500 | 0.3169 | 0.2535 |
67
+ | 0.1636 | 3.02 | 6000 | 0.3122 | 0.2465 |
68
+ | 0.137 | 3.27 | 6500 | 0.3054 | 0.2382 |
69
+ | 0.1311 | 3.52 | 7000 | 0.2956 | 0.2280 |
70
+ | 0.1261 | 3.77 | 7500 | 0.2898 | 0.2236 |
71
+ | 0.1187 | 4.02 | 8000 | 0.2847 | 0.2176 |
72
+ | 0.1011 | 4.27 | 8500 | 0.2763 | 0.2124 |
73
+ | 0.0981 | 4.52 | 9000 | 0.2754 | 0.2115 |
74
 
75
 
76
  ### Framework versions