seq-xls-r-fleurs_nl-run2-asr_af-run4
This model is a fine-tuned version of lucas-meyer/xls-r-fleurs_nl-run2 on the asr_af dataset. It achieves the following results:
- Wer (Validation): 40.41%
- Wer (Test): 42.25%
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 3
- total_train_batch_size: 12
- 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) |
---|---|---|---|---|
3.6881 | 1.76 | 400 | 0.7778 | 0.5874 |
0.5244 | 3.52 | 800 | 0.4591 | 0.4043 |
0.2724 | 5.29 | 1200 | 0.4899 | 0.4043 |
0.1857 | 7.05 | 1600 | 0.5125 | 0.3797 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 2
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.