wav2vec2-base-finetuned-ks-balanced3
This model was trained from scratch on the superb dataset. It achieves the following results on the evaluation set:
- Loss: 0.3610
- Accuracy: 0.9059
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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.1553 | 0.99 | 79 | 0.3610 | 0.9059 |
0.1672 | 1.99 | 159 | 0.5316 | 0.8569 |
0.1428 | 3.0 | 239 | 0.4606 | 0.8670 |
0.1477 | 4.0 | 319 | 0.4181 | 0.8825 |
0.1226 | 4.95 | 395 | 0.4867 | 0.8711 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
- Downloads last month
- 7
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.