whisper_final_nosp
This model is a fine-tuned version of openai/whisper-tiny on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0732
- Train Accuracy: 0.0234
- Validation Loss: 0.8512
- Validation Accuracy: 0.0203
- Epoch: 24
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:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
---|---|---|---|---|
7.5559 | 0.0010 | 6.3853 | 0.0013 | 0 |
6.3227 | 0.0021 | 5.7023 | 0.0038 | 1 |
4.9825 | 0.0063 | 3.6302 | 0.0109 | 2 |
2.9413 | 0.0126 | 2.1959 | 0.0154 | 3 |
1.9349 | 0.0157 | 1.6630 | 0.0172 | 4 |
1.4741 | 0.0171 | 1.3813 | 0.0181 | 5 |
1.1975 | 0.0181 | 1.2161 | 0.0186 | 6 |
1.0048 | 0.0188 | 1.0990 | 0.0191 | 7 |
0.8598 | 0.0194 | 1.0165 | 0.0194 | 8 |
0.7431 | 0.0199 | 0.9603 | 0.0196 | 9 |
0.6489 | 0.0203 | 0.9106 | 0.0198 | 10 |
0.5682 | 0.0207 | 0.8787 | 0.0199 | 11 |
0.4985 | 0.0210 | 0.8548 | 0.0200 | 12 |
0.4372 | 0.0213 | 0.8352 | 0.0201 | 13 |
0.3829 | 0.0216 | 0.8190 | 0.0202 | 14 |
0.3327 | 0.0219 | 0.8148 | 0.0202 | 15 |
0.2904 | 0.0221 | 0.8139 | 0.0202 | 16 |
0.2492 | 0.0224 | 0.8188 | 0.0202 | 17 |
0.2140 | 0.0226 | 0.8146 | 0.0203 | 18 |
0.1825 | 0.0228 | 0.8115 | 0.0203 | 19 |
0.1538 | 0.0229 | 0.8228 | 0.0203 | 20 |
0.1293 | 0.0231 | 0.8341 | 0.0202 | 21 |
0.1070 | 0.0232 | 0.8404 | 0.0202 | 22 |
0.0889 | 0.0233 | 0.8569 | 0.0202 | 23 |
0.0732 | 0.0234 | 0.8512 | 0.0203 | 24 |
Framework versions
- Transformers 4.25.0.dev0
- TensorFlow 2.9.2
- Datasets 2.6.1
- Tokenizers 0.13.2
- Downloads last month
- 3
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.