wav2vec2-animal-sounds-finetuned
This model is a fine-tuned version of facebook/wav2vec2-base-960h on the ESC-50 Animals Subset dataset. It achieves the following results on the evaluation set:
- Loss: 3.6753
- Accuracy: 0.04
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.8434 | 1.0 | 113 | 3.7969 | 0.055 |
| 3.7516 | 2.0 | 226 | 3.7279 | 0.04 |
| 3.7121 | 3.0 | 339 | 3.6753 | 0.04 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.3.0+cpu
- Tokenizers 0.20.3
- Downloads last month
- 129
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for a52103/wav2vec2-animal-sounds-finetuned
Base model
facebook/wav2vec2-base-960h