metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
name: wav2vec2-base-finetuned-ks
wav2vec2-base-finetuned-ks
This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0123
- Accuracy: 0.9984
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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 |
|---|---|---|---|---|
| 0.0779 | 1.0 | 80 | 0.1391 | 0.9641 |
| 0.0244 | 2.0 | 160 | 0.0304 | 0.9953 |
| 0.0045 | 3.0 | 240 | 0.0290 | 0.9938 |
| 0.0057 | 4.0 | 320 | 0.0204 | 0.9953 |
| 0.0025 | 5.0 | 400 | 0.0123 | 0.9984 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.9.1
- Datasets 1.18.4
- Tokenizers 0.10.3