metadata
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
- automatic-speech-recognition
- DewiBrynJones/banc-trawsgrifiadau-bangor-clean-with-ccv
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-xlsr-53-ft-btb-ccv-cy
results: []
wav2vec2-xlsr-53-ft-btb-ccv-cy
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the DEWIBRYNJONES/BANC-TRAWSGRIFIADAU-BANGOR-CLEAN-WITH-CCV - DEFAULT dataset. It achieves the following results on the evaluation set:
- Loss: 0.5865
- Wer: 0.4452
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: 8
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 600
- training_steps: 6000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 4.7051 | 0.0321 | 500 | 1.6562 | 0.9355 |
| 1.0362 | 0.0641 | 1000 | 1.1840 | 0.7978 |
| 0.811 | 0.0962 | 1500 | 1.0081 | 0.7175 |
| 0.6903 | 0.1283 | 2000 | 0.8935 | 0.6401 |
| 0.6238 | 0.1603 | 2500 | 0.8060 | 0.5849 |
| 0.5649 | 0.1924 | 3000 | 0.7770 | 0.5589 |
| 0.5309 | 0.2244 | 3500 | 0.7264 | 0.5327 |
| 0.4892 | 0.2565 | 4000 | 0.6865 | 0.5106 |
| 0.4521 | 0.2886 | 4500 | 0.6478 | 0.4861 |
| 0.4309 | 0.3206 | 5000 | 0.6222 | 0.4763 |
| 0.4055 | 0.3527 | 5500 | 0.5988 | 0.4526 |
| 0.3896 | 0.3848 | 6000 | 0.5865 | 0.4452 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1