metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: 241103_wav2vec2_Augmented_Dataset
results: []
241103_wav2vec2_Augmented_Dataset
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: 1.8498
- Wer: 1.0
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 1.0 | 40 | 2.9710 | 1.0 |
| No log | 2.0 | 80 | 2.7891 | 1.0 |
| No log | 3.0 | 120 | 2.5475 | 1.0 |
| No log | 4.0 | 160 | 2.3348 | 1.0 |
| No log | 5.0 | 200 | 2.1432 | 1.0 |
| No log | 6.0 | 240 | 1.9868 | 1.0 |
| No log | 7.0 | 280 | 1.9007 | 1.0 |
| No log | 8.0 | 320 | 1.8498 | 1.0 |
Framework versions
- Transformers 4.43.3
- Pytorch 2.5.1+cu124
- Datasets 2.19.2
- Tokenizers 0.19.1