metadata
library_name: transformers
license: mit
base_model: facebook/w2v-bert-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: w2v-bert-2.0-zuluMDD
results: []
w2v-bert-2.0-zuluMDD
This model is a fine-tuned version of facebook/w2v-bert-2.0 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9443
- Wer: 0.6667
- Cer: 0.1413
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 2.9185 | 3.8462 | 300 | 1.3991 | 0.7580 | 0.3175 |
| 0.18 | 7.6923 | 600 | 0.9443 | 0.6667 | 0.1413 |
Framework versions
- Transformers 4.48.1
- Pytorch 2.6.0+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0