metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- accuracy
- f1
model-index:
- name: wav2vec2-base-finetuned-ks
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: audiofolder
type: audiofolder
config: Data_Train
split: train
args: Data_Train
metrics:
- name: Accuracy
type: accuracy
value: 0.8127696289905091
- name: F1
type: f1
value: 0.7948883642136002
wav2vec2-base-finetuned-ks
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: 0.9323
- Accuracy: 0.8128
- F1: 0.7949
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.844 | 1.0 | 1449 | 1.7968 | 0.5065 | 0.3818 |
| 0.8796 | 2.0 | 2898 | 1.1875 | 0.6799 | 0.6273 |
| 0.7076 | 3.0 | 4347 | 1.0995 | 0.7584 | 0.7287 |
| 0.4669 | 4.0 | 5796 | 0.9960 | 0.7886 | 0.7675 |
| 0.2156 | 5.0 | 7245 | 0.9323 | 0.8128 | 0.7949 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3