xls-r-fleurs_zu-run1
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the FLEURS (zu) dataset. It achieves the following results:
- Wer (Validation): 61.41%
- Wer (Test): 60.23%
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) |
|---|---|---|---|---|
| 3.004700 | 1.03 | 250 | 2.994741 | 1.000000 |
| 0.506900 | 2.05 | 500 | 0.662974 | 0.716426 |
| 0.250800 | 3.08 | 750 | 0.577737 | 0.639608 |
| 0.169900 | 4.11 | 1000 | 0.578752 | 0.600381 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 5
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.