Hugging Face's logo

DewiBrynJones
/
wav2vec2-btb-cv-ft-btb-cy

Automatic Speech Recognition
TensorBoard
Safetensors
wav2vec2
./data-configs/btb.json
Generated from Trainer
Model card Files Metrics Community
DewiBrynJones commited on
Commit
e4f688b
•
1 Parent(s): d963512

Model save

Browse files
Files changed (1) hide show
  1. README.md +15 -17
README.md CHANGED
@@ -1,9 +1,7 @@
1
  ---
2
  license: apache-2.0
3
- base_model: DewiBrynJones/wav2vec2-xlsr-53-ft-btb-ccv-cy
4
  tags:
5
- - automatic-speech-recognition
6
- - ./data-configs/btb.json
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-btb-cv-ft-btb-cy
19
 
20
- This model is a fine-tuned version of [DewiBrynJones/wav2vec2-xlsr-53-ft-btb-ccv-cy](https://huggingface.co/DewiBrynJones/wav2vec2-xlsr-53-ft-btb-ccv-cy) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.4557
23
- - Wer: 0.3396
24
 
25
  ## Model description
26
 
@@ -53,17 +51,17 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:------:|:----:|:---------------:|:------:|
56
- | No log | 0.1139 | 200 | 0.6802 | 0.5026 |
57
- | No log | 0.2278 | 400 | 0.6103 | 0.4519 |
58
- | 1.9206 | 0.3417 | 600 | 0.5974 | 0.4537 |
59
- | 1.9206 | 0.4556 | 800 | 0.5455 | 0.4205 |
60
- | 0.6974 | 0.5695 | 1000 | 0.5195 | 0.4027 |
61
- | 0.6974 | 0.6834 | 1200 | 0.5081 | 0.3879 |
62
- | 0.6974 | 0.7973 | 1400 | 0.4813 | 0.3726 |
63
- | 0.6384 | 0.9112 | 1600 | 0.4656 | 0.3612 |
64
- | 0.6384 | 1.0251 | 1800 | 0.4568 | 0.3529 |
65
- | 0.5551 | 1.1390 | 2000 | 0.4594 | 0.3417 |
66
- | 0.5551 | 1.2528 | 2200 | 0.4557 | 0.3396 |
67
 
68
 
69
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: DewiBrynJones/wav2vec2-xlsr-53-ft-btb-cv-cy
4
  tags:
 
 
5
  - generated_from_trainer
6
  metrics:
7
  - wer
 
15
 
16
  # wav2vec2-btb-cv-ft-btb-cy
17
 
18
+ This model is a fine-tuned version of [DewiBrynJones/wav2vec2-xlsr-53-ft-btb-cv-cy](https://huggingface.co/DewiBrynJones/wav2vec2-xlsr-53-ft-btb-cv-cy) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.4418
21
+ - Wer: 0.3371
22
 
23
  ## Model description
24
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:------:|:----:|:---------------:|:------:|
54
+ | No log | 0.1139 | 200 | 0.7154 | 0.4784 |
55
+ | No log | 0.2278 | 400 | 0.6105 | 0.4456 |
56
+ | 1.3805 | 0.3417 | 600 | 0.5903 | 0.4618 |
57
+ | 1.3805 | 0.4556 | 800 | 0.5655 | 0.4232 |
58
+ | 0.6886 | 0.5695 | 1000 | 0.5267 | 0.3967 |
59
+ | 0.6886 | 0.6834 | 1200 | 0.5074 | 0.3808 |
60
+ | 0.6886 | 0.7973 | 1400 | 0.4814 | 0.3667 |
61
+ | 0.6336 | 0.9112 | 1600 | 0.4642 | 0.3621 |
62
+ | 0.6336 | 1.0251 | 1800 | 0.4544 | 0.3472 |
63
+ | 0.5411 | 1.1390 | 2000 | 0.4474 | 0.3406 |
64
+ | 0.5411 | 1.2528 | 2200 | 0.4418 | 0.3371 |
65
 
66
 
67
  ### Framework versions