wav2vec2_batangueno-hp2
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: 0.4632
- Wer: 0.3485
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: 5.5860027851721875e-05
- train_batch_size: 4
- 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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.8461 | 5.32 | 500 | 2.6248 | 1.0 |
| 1.5848 | 10.64 | 1000 | 0.6266 | 0.5268 |
| 0.3678 | 15.96 | 1500 | 0.4632 | 0.3485 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu118
- Datasets 1.18.3
- Tokenizers 0.14.1
- Downloads last month
- 1
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.