metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- accuracy
model-index:
- name: my_awesome_mind_model
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: audiofolder
type: audiofolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9805375347544022
my_awesome_mind_model
This model is a fine-tuned version of facebook/wav2vec2-base on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1816
- Accuracy: 0.9805
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: 128
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- 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 |
|---|---|---|---|---|
| 2.267 | 1.0 | 120 | 2.0147 | 0.9626 |
| 1.309 | 2.0 | 240 | 1.0828 | 0.9731 |
| 0.8739 | 2.99 | 360 | 0.6753 | 0.9759 |
| 0.6183 | 4.0 | 481 | 0.4492 | 0.9781 |
| 0.4868 | 5.0 | 601 | 0.3346 | 0.9771 |
| 0.4124 | 6.0 | 721 | 0.2606 | 0.9787 |
| 0.3495 | 6.99 | 841 | 0.2214 | 0.9808 |
| 0.3073 | 8.0 | 962 | 0.2032 | 0.9790 |
| 0.3264 | 9.0 | 1082 | 0.1862 | 0.9812 |
| 0.3035 | 9.98 | 1200 | 0.1816 | 0.9805 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.0
- Datasets 2.15.0
- Tokenizers 0.15.0