metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- audio-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: wav2vec2-present
results: []
wav2vec2-present
This model is a fine-tuned version of facebook/wav2vec2-base on the MatsRooth/prosodic_minimal dataset. It achieves the following results on the evaluation set:
- Loss: 0.1188
- Accuracy: 0.9783
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: 3e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 0
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5859 | 1.0 | 2151 | 0.2952 | 0.9351 |
| 0.4323 | 2.0 | 4302 | 0.2043 | 0.9562 |
| 0.4494 | 3.0 | 6453 | 0.1691 | 0.9644 |
| 0.0351 | 4.0 | 8604 | 0.1447 | 0.9677 |
| 0.2679 | 5.0 | 10755 | 0.1372 | 0.9704 |
| 0.3252 | 6.0 | 12906 | 0.1281 | 0.9720 |
| 0.1319 | 7.0 | 15057 | 0.1087 | 0.9789 |
| 0.0646 | 8.0 | 17208 | 0.1371 | 0.9740 |
| 0.1035 | 9.0 | 19359 | 0.1219 | 0.9776 |
| 0.1148 | 10.0 | 21510 | 0.1188 | 0.9783 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.9.0+cu128
- Datasets 2.13.1
- Tokenizers 0.15.0