metadata
license: apache-2.0
base_model: FerhatDk/wav2vec2-base_music_speech_both_classification
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: wav2vec2-base_music_speech_both_classification-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: 0.85
wav2vec2-base_music_speech_both_classification-finetuned-gtzan
This model is a fine-tuned version of FerhatDk/wav2vec2-base_music_speech_both_classification on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.6167
- Accuracy: 0.85
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0009 | 1.0 | 56 | 1.8533 | 0.31 |
| 1.4898 | 1.99 | 112 | 1.3633 | 0.45 |
| 1.1394 | 2.99 | 168 | 1.1963 | 0.61 |
| 0.9214 | 4.0 | 225 | 0.8506 | 0.73 |
| 0.6922 | 5.0 | 281 | 0.8479 | 0.78 |
| 0.687 | 5.99 | 337 | 0.7577 | 0.81 |
| 0.5052 | 6.99 | 393 | 0.7833 | 0.78 |
| 0.3733 | 8.0 | 450 | 0.6448 | 0.83 |
| 0.2137 | 9.0 | 506 | 0.5698 | 0.83 |
| 0.2863 | 9.96 | 560 | 0.6167 | 0.85 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3