wav2vec2-large-xlsr-53-sw-ke-tokenizer

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the fleurs dataset. It achieves the following results on the evaluation set:

• Loss: 0.9600
• Wer: 0.6224

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: 0.0003
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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: 500
• num_epochs: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
5.8918	4.1667	400	2.8681	1.0
2.8863	8.3333	800	2.8663	1.0
2.8092	12.5	1200	2.5442	1.0
0.8899	16.6667	1600	0.6992	0.6511
0.2577	20.8333	2000	0.8239	0.6385
0.1397	25.0	2400	0.8893	0.6251
0.0971	29.1667	2800	0.9600	0.6224

Framework versions

• Transformers 4.53.0
• Pytorch 2.7.1+cu126
• Datasets 3.6.0
• Tokenizers 0.21.2