|
--- |
|
license: apache-2.0 |
|
base_model: jonatasgrosman/wav2vec2-xls-r-1b-portuguese |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: wav2vec2-xls-r-1b-medical-domain |
|
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-xls-r-1b-medical-domain |
|
|
|
This model is a fine-tuned version of [jonatasgrosman/wav2vec2-xls-r-1b-portuguese](https://huggingface.co/jonatasgrosman/wav2vec2-xls-r-1b-portuguese) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5363 |
|
- Wer: 0.7022 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 20 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-------:|:----:|:---------------:|:------:| |
|
| No log | 9.9379 | 200 | 0.2631 | 0.3790 | |
|
| 1.2151 | 19.8758 | 400 | 0.5363 | 0.7022 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.1 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
