metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: facebook/wav2vec2-base-100k-voxpopuli
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: wav2vec2-base-100k-voxpopuli-finetuned-gtzan
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: GTZAN
type: marsyas/gtzan
config: all
split: train
args: all
metrics:
- name: Accuracy
type: accuracy
value: 0.84
wav2vec2-base-100k-voxpopuli-finetuned-gtzan
This model is a fine-tuned version of facebook/wav2vec2-base-100k-voxpopuli on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 1.0838
- Accuracy: 0.84
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Use adamw_torch_fused 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0777 | 1.0 | 8 | 0.9974 | 0.86 |
| 0.0276 | 2.0 | 16 | 1.1353 | 0.83 |
| 0.326 | 3.0 | 24 | 1.2362 | 0.81 |
| 0.123 | 4.0 | 32 | 1.1119 | 0.84 |
| 0.0225 | 5.0 | 40 | 1.1009 | 0.85 |
| 0.0776 | 6.0 | 48 | 1.0709 | 0.85 |
| 0.025 | 7.0 | 56 | 1.1126 | 0.84 |
| 0.0163 | 8.0 | 64 | 1.0823 | 0.84 |
| 0.0193 | 9.0 | 72 | 1.0818 | 0.84 |
| 0.0209 | 10.0 | 80 | 1.0838 | 0.84 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu128
- Datasets 3.6.0
- Tokenizers 0.22.1