Whisper Small Tw - Lagyamfi_v2
This model is a fine-tuned version of openai/whisper-small on the akan audio dataset. It achieves the following results on the evaluation set:
- Loss: 0.6401
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: 0.001
- train_batch_size: 16
- 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: 50
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7315 | 1.0 | 137 | 0.7419 |
| 0.4855 | 2.0 | 274 | 0.5828 |
| 0.335 | 3.0 | 411 | 0.5613 |
| 0.2071 | 4.0 | 548 | 0.5593 |
| 0.129 | 5.0 | 685 | 0.5512 |
| 0.0691 | 6.0 | 822 | 0.5786 |
| 0.0394 | 7.0 | 959 | 0.5997 |
| 0.0168 | 8.0 | 1096 | 0.6296 |
| 0.0111 | 9.0 | 1233 | 0.6353 |
| 0.0082 | 10.0 | 1370 | 0.6401 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.
Model tree for Lagyamfi/int8-whisper-large-v2-asr
Base model
openai/whisper-small