wav2vec2-base-asr-minds14

This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.8823
• Wer: 0.9864

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 4
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.0228	8.8533	1000	3.0009	1.0
2.9639	17.7022	2000	2.9597	1.0
2.8934	26.5511	3000	2.9301	1.0
2.8322	35.4	4000	2.8995	0.9995
2.7889	44.2489	5000	2.8823	0.9864

Framework versions

• Transformers 4.55.2
• Pytorch 2.8.0+cu128
• Datasets 3.6.0
• Tokenizers 0.21.4