|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: seq-xls-r-fleurs_nl-run2-asr_af-run7 |
|
results: [] |
|
datasets: |
|
- lucas-meyer/asr_af |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# seq-xls-r-fleurs_nl-run2-asr_af-run7 |
|
|
|
This model is a fine-tuned version of [lucas-meyer/xls-r-fleurs_nl-run2](https://huggingface.co/lucas-meyer/xls-r-fleurs_nl-run2) on the asr_af dataset. |
|
It achieves the following results: |
|
- Wer (Validation): 36.72% |
|
- Wer (Test): 37.16% |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 0.0003 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- 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: 30 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer (Train) | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 4.8229 | 1.47 | 250 | 2.7832 | 0.9998 | |
|
| 1.1565 | 2.93 | 500 | 0.5693 | 0.4932 | |
|
| 0.3893 | 4.4 | 750 | 0.4765 | 0.4026 | |
|
| 0.2536 | 5.87 | 1000 | 0.3951 | 0.3669 | |
|
| 0.1756 | 7.33 | 1250 | 0.4565 | 0.3814 | |
|
| 0.1384 | 8.8 | 1500 | 0.4923 | 0.3606 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
