MU-Bench: Benchmarking Machine Unlearning
Collection
Benchmark machine unlearning (MU) in a wide range of tasks, domains, modalities. • 18 items • Updated • 1
# Load model directly
from transformers import AutoProcessor, AutoModelForAudioClassification
processor = AutoProcessor.from_pretrained("jialicheng/whisper-base-speech_commands")
model = AutoModelForAudioClassification.from_pretrained("jialicheng/whisper-base-speech_commands")Quick Links
superb_ks_42
This model is a fine-tuned version of openai/whisper-base on the superb dataset. It achieves the following results on the evaluation set:
- Loss: 0.1152
- Accuracy: 0.9834
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6909 | 1.0 | 1597 | 0.1572 | 0.9651 |
| 0.0891 | 2.0 | 3194 | 0.1597 | 0.9660 |
| 0.0676 | 3.0 | 4791 | 0.1304 | 0.9719 |
| 0.0475 | 4.0 | 6388 | 0.0999 | 0.9796 |
| 0.0433 | 5.0 | 7985 | 0.1079 | 0.9798 |
| 0.0284 | 6.0 | 9582 | 0.1089 | 0.9803 |
| 0.0236 | 7.0 | 11179 | 0.1162 | 0.9819 |
| 0.0193 | 8.0 | 12776 | 0.1152 | 0.9834 |
| 0.0111 | 9.0 | 14373 | 0.1272 | 0.9821 |
| 0.0088 | 10.0 | 15970 | 0.1306 | 0.9826 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 6
Model tree for jialicheng/whisper-base-speech_commands
Base model
openai/whisper-baseDataset used to train jialicheng/whisper-base-speech_commands
Collection including jialicheng/whisper-base-speech_commands
Evaluation results
- Accuracy on superbvalidation set self-reported0.983
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="jialicheng/whisper-base-speech_commands")