audio_cls_hhd

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.6539
• Accuracy: 0.0504

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• 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
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	15	2.6427	0.0588
No log	2.0	30	2.6482	0.0420
No log	3.0	45	2.6493	0.0588
No log	4.0	60	2.6610	0.0588
No log	5.0	75	2.6633	0.0588
No log	6.0	90	2.6627	0.0672
No log	7.0	105	2.6633	0.0840
No log	8.0	120	2.6583	0.0504
No log	9.0	135	2.6541	0.0504
No log	10.0	150	2.6539	0.0504

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1