metadata
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
- automatic-speech-recognition
- DewiBrynJones/banc-trawsgrifiadau-bangor-clean
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-xlsr-53-ft-btb-cy
results: []
wav2vec2-xlsr-53-ft-btb-cy
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the DEWIBRYNJONES/BANC-TRAWSGRIFIADAU-BANGOR-CLEAN - DEFAULT dataset. It achieves the following results on the evaluation set:
- Loss: 0.8192
- Wer: 0.4756
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 2500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 0.2278 | 200 | 2.9657 | 1.0 |
| No log | 0.4556 | 400 | 1.2565 | 0.8238 |
| 3.3708 | 0.6834 | 600 | 0.8799 | 0.6337 |
| 3.3708 | 0.9112 | 800 | 0.7572 | 0.5468 |
| 0.9128 | 1.1390 | 1000 | 0.6134 | 0.4571 |
| 0.9128 | 1.3667 | 1200 | 0.5879 | 0.4429 |
| 0.9128 | 1.5945 | 1400 | 0.6283 | 0.4655 |
| 0.7779 | 1.8223 | 1600 | 0.6166 | 0.4566 |
| 0.7779 | 2.0501 | 1800 | 0.6131 | 0.4648 |
| 0.7465 | 2.2779 | 2000 | 0.6312 | 0.4722 |
| 0.7465 | 2.5057 | 2200 | 0.7630 | 0.4722 |
| 0.7465 | 2.7335 | 2400 | 0.8068 | 0.4827 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1