wav2vec2-48KHz-audioset-natual-sounds

This model is a fine-tuned version of bilalhsp/wav2vec2-base-audioset-natural-sounds on the generator dataset.

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: 16
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Contrastive Loss	Diversity Loss
No log	1.0	8	1965.5140	1933.3790	321.3505

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu118
• Datasets 2.20.0
• Tokenizers 0.19.1