openai/whisper-small-finetuned-gtzan
This model is a fine-tuned version of openai/whisper-tiny on the minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7962
- Wer Ortho: 0.2622
- Wer: 0.2674
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0001 | 17.2414 | 500 | 0.6029 | 0.2548 | 0.2580 |
| 0.0 | 34.4828 | 1000 | 0.6568 | 0.2480 | 0.2532 |
| 0.0 | 51.7241 | 1500 | 0.6910 | 0.2498 | 0.2556 |
| 0.0 | 68.9655 | 2000 | 0.7173 | 0.2480 | 0.2538 |
| 0.0 | 86.2069 | 2500 | 0.7402 | 0.2486 | 0.2544 |
| 0.0 | 103.4483 | 3000 | 0.7624 | 0.2566 | 0.2621 |
| 0.0 | 120.6897 | 3500 | 0.7800 | 0.2640 | 0.2692 |
| 0.0 | 137.9310 | 4000 | 0.7962 | 0.2622 | 0.2674 |
Framework versions
- Transformers 4.43.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 63
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.