<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
whisper-small-keyword-spotting-m-agv-grabo
This model is a fine-tuned version of openai/whisper-small on the kw-spotting-fsc-sl-agv dataset. It achieves the following results on the evaluation set:
- Loss: 0.1700
- Accuracy: 0.9227
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: 32
- eval_batch_size: 32
- seed: 0
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2841 | 1.0 | 723 | 0.1700 | 0.9227 |
| 0.1826 | 2.0 | 1446 | 0.2144 | 0.9147 |
| 0.2425 | 3.0 | 2169 | 0.1962 | 0.9144 |
| 0.164 | 4.0 | 2892 | 0.3100 | 0.8865 |
| 0.1525 | 5.0 | 3615 | 0.2824 | 0.9000 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.0
- Datasets 2.14.6
- Tokenizers 0.14.1
