speecht5_finetuned_np_adhikari_e20

This model is a fine-tuned version of evolt/speecht5_finetuned_np_adhikari on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4079

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: 4
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• 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: 100
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.464	1.7982	100	0.4331
0.462	3.5805	200	0.4262
0.4381	5.3628	300	0.4324
0.436	7.1451	400	0.4237
0.4368	8.9433	500	0.4170
0.4383	10.7256	600	0.4121
0.4312	12.5079	700	0.4145
0.411	14.2902	800	0.4126
0.4063	16.0726	900	0.4093
0.4217	17.8707	1000	0.4079

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1