data2vec-audio-base-960h-ft
This model is a fine-tuned version of facebook/data2vec-audio-base-960h on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0146
- Accuracy: 0.9967
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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 | Accuracy | Validation Loss |
|---|---|---|---|---|
| 0.1427 | 1.0 | 8558 | 0.9941 | 0.0271 |
| 0.0799 | 2.0 | 17116 | 0.9964 | 0.0154 |
| 0.0889 | 3.0 | 25674 | 0.9967 | 0.0146 |
| 0.0843 | 4.0 | 34232 | 0.9967 | 0.0162 |
| 0.0925 | 5.0 | 42790 | 0.9961 | 0.0151 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cpu
- Datasets 2.10.1
- Tokenizers 0.12.1
- Downloads last month
- 132
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.