metadata
library_name: transformers
license: bsd-3-clause
base_model: MIT/ast-finetuned-audioset-12-12-0.447
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- precision
- recall
- f1
model-index:
- name: ast-mlcommons-speech-commands
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: audiofolder
type: audiofolder
config: default
split: validation
args: default
metrics:
- name: Precision
type: precision
value: 0.9661601051155746
- name: Recall
type: recall
value: 0.9662664379645511
- name: F1
type: f1
value: 0.9661541075893276
ast-mlcommons-speech-commands
This model is a fine-tuned version of MIT/ast-finetuned-audioset-12-12-0.447 on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1790
- Precision: 0.9662
- Recall: 0.9663
- F1: 0.9662
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | F1 | Validation Loss | Precision | Recall |
|---|---|---|---|---|---|---|
| 0.0795 | 1.0 | 3496 | 0.9342 | 0.2169 | 0.9357 | 0.9347 |
| 0.1295 | 2.0 | 6992 | 0.9467 | 0.1728 | 0.9486 | 0.9473 |
| 0.0279 | 3.0 | 10488 | 0.9551 | 0.1717 | 0.9558 | 0.9556 |
| 0.0029 | 4.0 | 13984 | 0.9621 | 0.1733 | 0.9624 | 0.9621 |
| 0.0023 | 5.0 | 17480 | 0.9662 | 0.1790 | 0.9663 | 0.9662 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.7.0+cu128
- Datasets 3.6.0
- Tokenizers 0.21.1