metadata
license: apache-2.0
tags:
- generated_from_trainer
base_model: facebook/wav2vec2-base
metrics:
- wer
model-index:
- name: wav2vec2
results: []
wav2vec2
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4145
- Wer: 0.4598
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2000
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 4.245 | 9.26 | 500 | 2.9303 | 0.9871 |
| 2.5133 | 18.52 | 1000 | 1.3210 | 0.6705 |
| 0.6779 | 27.78 | 1500 | 1.2663 | 0.4949 |
| 0.3209 | 37.04 | 2000 | 1.3584 | 0.4872 |
| 0.19 | 46.3 | 2500 | 1.4145 | 0.4598 |
Framework versions
- Transformers 4.39.2
- Pytorch 1.12.1+cu116
- Datasets 2.18.0
- Tokenizers 0.15.2