speecht5_tts_id_octava

This model is a fine-tuned version of microsoft/speecht5_tts on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4595

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: 4
• eval_batch_size: 2
• seed: 42
• 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: 4000

Training results

Training Loss	Epoch	Step	Validation Loss
0.6166	0.0928	500	0.5342
0.5688	0.1855	1000	0.5005
0.5256	0.2783	1500	0.4776
0.5293	0.3711	2000	0.4739
0.5166	0.4638	2500	0.4702
0.5016	0.5566	3000	0.4617
0.4972	0.6494	3500	0.4622
0.4958	0.7421	4000	0.4595

Framework versions

• Transformers 4.56.2
• Pytorch 2.8.0+cu129
• Datasets 3.6.0
• Tokenizers 0.22.1