wav2vec2-base-finetuned-ks
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: 0.0817
- Accuracy: 0.9844
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: 42
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6386 | 1.0 | 399 | 0.5305 | 0.9601 |
| 0.2358 | 2.0 | 798 | 0.1774 | 0.9747 |
| 0.1982 | 3.0 | 1197 | 0.1172 | 0.9794 |
| 0.1554 | 4.0 | 1596 | 0.0884 | 0.9835 |
| 0.1261 | 5.0 | 1995 | 0.0817 | 0.9844 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 1.18.4
- Tokenizers 0.11.6
- Downloads last month
- 5
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.