metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: wav2vec2-base-finetuned-ks-verbinden4
results: []
wav2vec2-base-finetuned-ks-verbinden4
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: 0.0089
- Accuracy: 0.9986
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 |
|---|---|---|---|---|
| 0.062 | 1.0 | 290 | 0.0571 | 0.9909 |
| 0.0193 | 2.0 | 581 | 0.0332 | 0.9930 |
| 0.0254 | 3.0 | 871 | 0.0089 | 0.9986 |
| 0.0187 | 4.0 | 1162 | 0.0094 | 0.9981 |
| 0.0081 | 4.99 | 1450 | 0.0128 | 0.9966 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0