metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
datasets:
- minds14
metrics:
- accuracy
model-index:
- name: ft-wav2vec2-with-minds
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: minds14
type: minds14
config: en-US
split: train
args: en-US
metrics:
- name: Accuracy
type: accuracy
value: 0.07964601769911504
ft-wav2vec2-with-minds
This model is a fine-tuned version of facebook/wav2vec2-base on the minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 2.6507
- Accuracy: 0.0796
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- 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
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 1.0 | 2 | 2.6510 | 0.0088 |
No log | 2.0 | 4 | 2.6535 | 0.0265 |
No log | 3.0 | 6 | 2.6496 | 0.0442 |
No log | 4.0 | 8 | 2.6469 | 0.0531 |
2.6324 | 5.0 | 10 | 2.6446 | 0.0619 |
2.6324 | 6.0 | 12 | 2.6507 | 0.0796 |
2.6324 | 7.0 | 14 | 2.6551 | 0.0619 |
2.6324 | 8.0 | 16 | 2.6529 | 0.0531 |
2.6324 | 9.0 | 18 | 2.6497 | 0.0619 |
2.6299 | 10.0 | 20 | 2.6503 | 0.0619 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.0
- Datasets 2.15.0
- Tokenizers 0.15.0