metadata
license: apache-2.0
base_model: facebook/wav2vec2-base-960h
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: wav2vec2-base-960h-finetuned-gtzan-v1
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: 0.73
wav2vec2-base-960h-finetuned-gtzan-v1
This model is a fine-tuned version of facebook/wav2vec2-base-960h on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.9585
- Accuracy: 0.73
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: 8
- eval_batch_size: 8
- seed: 42
- 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 |
|---|---|---|---|---|
| 2.2779 | 1.0 | 113 | 2.2108 | 0.15 |
| 2.2332 | 2.0 | 226 | 2.2445 | 0.22 |
| 1.9418 | 3.0 | 339 | 1.8945 | 0.27 |
| 1.654 | 4.0 | 452 | 1.6766 | 0.33 |
| 1.4822 | 5.0 | 565 | 1.6078 | 0.53 |
| 1.3172 | 6.0 | 678 | 1.3317 | 0.55 |
| 1.2133 | 7.0 | 791 | 1.2287 | 0.65 |
| 0.9575 | 8.0 | 904 | 1.0401 | 0.63 |
| 0.8893 | 9.0 | 1017 | 0.9700 | 0.71 |
| 0.9531 | 10.0 | 1130 | 0.9585 | 0.73 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0