metadata
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: wav2vec2-base-voxceleb1
results: []
wav2vec2-base-voxceleb1
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0316
- Accuracy: 0.8311
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 1
- seed: 1016
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 5.7408 | 1.0 | 8648 | 6.0003 | 0.0198 |
| 3.0546 | 2.0 | 17296 | 3.9534 | 0.2351 |
| 1.3947 | 3.0 | 25944 | 2.4203 | 0.4975 |
| 0.5969 | 4.0 | 34592 | 1.5746 | 0.6645 |
| 0.2713 | 5.0 | 43240 | 1.3448 | 0.7310 |
| 0.1379 | 6.0 | 51888 | 1.2183 | 0.7664 |
| 0.0555 | 7.0 | 60536 | 1.1041 | 0.7956 |
| 0.0268 | 8.0 | 69184 | 1.0941 | 0.8104 |
| 0.0122 | 9.0 | 77832 | 1.0580 | 0.8256 |
| 0.0053 | 10.0 | 86480 | 1.0316 | 0.8311 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.0.0+cu117
- Datasets 3.1.0
- Tokenizers 0.20.3