miosipof/whisper-small-ft-balbus-sep28k-v1
This model is a fine-tuned version of openai/whisper-small on the Apple dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.5668
- Accuracy: 0.7954
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 404 | 0.4751 | 0.7748 |
| 0.494 | 2.0 | 808 | 0.4533 | 0.7901 |
| 0.3256 | 3.0 | 1212 | 0.5668 | 0.7954 |
Framework versions
- Transformers 4.48.1
- Pytorch 2.2.0
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 7
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for miosipof/whisper-small-ft-balbus-sep28k-v1
Base model
openai/whisper-small