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: 0.5418
- Wer: 0.3991
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: 200
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 0.2278 | 200 | 2.7455 | 1.0 |
| No log | 0.4556 | 400 | 1.1437 | 0.7406 |
| 2.6988 | 0.6834 | 600 | 0.7286 | 0.5377 |
| 2.6988 | 0.9112 | 800 | 0.6604 | 0.4897 |
| 0.8304 | 1.1390 | 1000 | 0.5619 | 0.4339 |
| 0.8304 | 1.3667 | 1200 | 0.5692 | 0.4245 |
| 0.8304 | 1.5945 | 1400 | 0.5639 | 0.4210 |
| 0.71 | 1.8223 | 1600 | 0.5502 | 0.4186 |
| 0.71 | 2.0501 | 1800 | 0.5441 | 0.4073 |
| 0.6605 | 2.2779 | 2000 | 0.5418 | 0.3991 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1