metadata
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- audio-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: wav2vec2-base-wakeword
results: []
wav2vec2-base-wakeword
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: 6.0557
- Accuracy: 0.6140
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: 512
- eval_batch_size: 32
- seed: 0
- gradient_accumulation_steps: 4
- total_train_batch_size: 2048
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 1 | 6.2039 | 0.0 |
| No log | 2.0 | 2 | 6.1510 | 0.0175 |
| No log | 3.0 | 3 | 6.0954 | 0.4386 |
| No log | 4.0 | 4 | 6.0688 | 0.5789 |
| No log | 5.0 | 5 | 6.0557 | 0.6140 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1