metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2_batangueno
results: []
wav2vec2_batangueno
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: 0.4998
- Wer: 0.2646
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: 6.642954074604246e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.8415 | 2.66 | 500 | 2.7515 | 1.0 |
| 1.7736 | 5.32 | 1000 | 1.1667 | 0.7086 |
| 0.5249 | 7.98 | 1500 | 0.6594 | 0.4936 |
| 0.2863 | 10.64 | 2000 | 0.5026 | 0.3514 |
| 0.2063 | 13.3 | 2500 | 0.4979 | 0.3287 |
| 0.1496 | 15.96 | 3000 | 0.5297 | 0.3298 |
| 0.1135 | 18.62 | 3500 | 0.4943 | 0.3094 |
| 0.0953 | 21.28 | 4000 | 0.5315 | 0.2855 |
| 0.0773 | 23.94 | 4500 | 0.5057 | 0.2844 |
| 0.0617 | 26.6 | 5000 | 0.5041 | 0.2686 |
| 0.0529 | 29.26 | 5500 | 0.4998 | 0.2646 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 1.18.3
- Tokenizers 0.14.1