swahili-w2v-bert

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: inf
• Wer: 0.2038

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: 1e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.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: 100
• training_steps: 2500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4225	0.2	500	inf	0.2852
0.307	0.4	1000	inf	0.2363
0.3984	0.6	1500	inf	0.2235
0.1242	0.8	2000	inf	0.2093
0.0832	1.0	2500	inf	0.2038

Framework versions

• Transformers 4.52.0
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.2