|
--- |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: wav2vec2_batangueno |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# wav2vec2_batangueno |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the [jrs-a/batangueno-accent](https://huggingface.co/datasets/jrs-a/batangueno-accent) dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5694 |
|
- Wer: 0.2635 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 3.8312 | 2.66 | 500 | 2.7217 | 1.0 | |
|
| 1.5348 | 5.32 | 1000 | 0.7723 | 0.5788 | |
|
| 0.5104 | 7.98 | 1500 | 0.5589 | 0.4308 | |
|
| 0.2845 | 10.64 | 2000 | 0.5485 | 0.3803 | |
|
| 0.1995 | 13.3 | 2500 | 0.5043 | 0.3273 | |
|
| 0.1493 | 15.96 | 3000 | 0.5247 | 0.3045 | |
|
| 0.1195 | 18.62 | 3500 | 0.5410 | 0.2984 | |
|
| 0.0974 | 21.28 | 4000 | 0.5905 | 0.2804 | |
|
| 0.0784 | 23.94 | 4500 | 0.5702 | 0.2780 | |
|
| 0.0601 | 26.6 | 5000 | 0.5678 | 0.2659 | |
|
| 0.0578 | 29.26 | 5500 | 0.5694 | 0.2635 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 1.18.3 |
|
- Tokenizers 0.14.1 |
|
|
