metadata
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- f1
- precision
- recall
model-index:
- name: 1.0.0
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: audiofolder
type: audiofolder
config: initial_audio
split: test
args: initial_audio
metrics:
- name: F1
type: f1
value: 0.11428571428571428
- name: Precision
type: precision
value: 0.6666666666666666
- name: Recall
type: recall
value: 0.0625
1.0.0
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: 0.6934
- F1: 0.1143
- Precision: 0.6667
- Recall: 0.0625
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall |
|---|---|---|---|---|---|---|
| No log | 1.0 | 2 | 0.6925 | 0.1176 | 1.0 | 0.0625 |
| No log | 2.0 | 4 | 0.6929 | 0.1081 | 0.4 | 0.0625 |
| No log | 3.0 | 6 | 0.6934 | 0.1143 | 0.6667 | 0.0625 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1
- Datasets 3.0.0
- Tokenizers 0.19.1