fil_b64_le5_s4000

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: 0.4125

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: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2000
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.575	22.2222	500	0.4967
0.4945	44.4444	1000	0.4460
0.4681	66.6667	1500	0.4301
0.4514	88.8889	2000	0.4194
0.4396	111.1111	2500	0.4129
0.432	133.3333	3000	0.4124
0.43	155.5556	3500	0.4104
0.4317	177.7778	4000	0.4125

Framework versions

• Transformers 4.41.0.dev0
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1