whisper-large-v2-Irish
This model is a fine-tuned version of kpriyanshu256/whisper-large-v2-cy-500-32-1e-05 on the Common Voice 11.0 and the FLEURS datasets. It achieves the following results on the evaluation set:
- Loss: 0.7879
- Wer: 34.2625
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3768 | 0.25 | 250 | 0.7143 | 39.4890 |
| 0.1498 | 1.15 | 500 | 0.7663 | 35.8014 |
| 0.0907 | 2.05 | 750 | 0.7730 | 35.2497 |
| 0.045 | 2.3 | 1000 | 0.7879 | 34.2625 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2