distilhubert-finetuned-speech_commands
This model is a fine-tuned version of ntu-spml/distilhubert on the Speech_command_RK dataset. It achieves the following results on the evaluation set:
- Loss: 0.1895
- Accuracy: 0.9976
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: 264
- eval_batch_size: 264
- 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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
2.1911 | 1.0 | 25 | 1.9352 | 0.8859 |
1.0366 | 2.0 | 50 | 0.8334 | 0.9915 |
0.4879 | 3.0 | 75 | 0.3774 | 0.9939 |
0.297 | 4.0 | 100 | 0.2254 | 0.9951 |
0.2422 | 5.0 | 125 | 0.1895 | 0.9976 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 25
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.