wav2vec2_milDB

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: 1.9031
• Wer: 1.0

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: 0.0001
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• 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
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.9166	10.9890	1000	1.6068	1.0
1.2813	21.9780	2000	1.6121	1.0
1.8313	32.9670	3000	1.8892	1.0
1.8958	43.9560	4000	1.8899	1.0
1.897	54.9451	5000	1.9031	1.0

Framework versions

• Transformers 4.49.0
• Pytorch 2.4.1+cu124
• Datasets 2.21.0
• Tokenizers 0.21.0