metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- audio-classification
- generated_from_trainer
datasets:
- superb
metrics:
- accuracy
model-index:
- name: wav2vec2-base-ft-keyword-spotting
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: superb
type: superb
config: ks
split: validation
args: ks
metrics:
- name: Accuracy
type: accuracy
value: 0.9832303618711385
wav2vec2-base-ft-keyword-spotting
This model is a fine-tuned version of facebook/wav2vec2-base on the superb dataset. It achieves the following results on the evaluation set:
- Loss: 0.0827
- Accuracy: 0.9832
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: 0
- 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: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4547 | 1.0 | 399 | 0.3372 | 0.9710 |
| 0.2625 | 2.0 | 798 | 0.1182 | 0.9779 |
| 0.1575 | 3.0 | 1197 | 0.0963 | 0.9787 |
| 0.1314 | 4.0 | 1597 | 0.0827 | 0.9832 |
| 0.1307 | 5.0 | 1995 | 0.0789 | 0.9831 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3