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: 0.4942
- Wer: 0.3917
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: 16
- 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: 300
- training_steps: 3000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 0.0672 | 200 | 2.9830 | 1.0 |
| No log | 0.1344 | 400 | 1.5613 | 0.9658 |
| 3.6118 | 0.2016 | 600 | 1.0701 | 0.7649 |
| 3.6118 | 0.2688 | 800 | 0.8868 | 0.6947 |
| 0.9333 | 0.3360 | 1000 | 0.7680 | 0.6071 |
| 0.9333 | 0.4032 | 1200 | 0.7224 | 0.5454 |
| 0.9333 | 0.4704 | 1400 | 0.6733 | 0.5122 |
| 0.7446 | 0.5376 | 1600 | 0.6437 | 0.4966 |
| 0.7446 | 0.6048 | 1800 | 0.6064 | 0.4774 |
| 0.6579 | 0.6720 | 2000 | 0.5674 | 0.4461 |
| 0.6579 | 0.7392 | 2200 | 0.5556 | 0.4325 |
| 0.6579 | 0.8065 | 2400 | 0.5264 | 0.4180 |
| 0.5823 | 0.8737 | 2600 | 0.5130 | 0.4022 |
| 0.5823 | 0.9409 | 2800 | 0.4982 | 0.3936 |
| 0.5426 | 1.0081 | 3000 | 0.4942 | 0.3917 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1