fil_b32_le5_s8000

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: 0.4039

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: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2000
• training_steps: 8000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.632	11.1111	500	0.5323
0.519	22.2222	1000	0.4494
0.4816	33.3333	1500	0.4291
0.481	44.4444	2000	0.4211
0.4459	55.5556	2500	0.4139
0.4484	66.6667	3000	0.4114
0.4317	77.7778	3500	0.4081
0.4301	88.8889	4000	0.4076
0.4274	100.0	4500	0.4059
0.4323	111.1111	5000	0.4062
0.4189	122.2222	5500	0.4045
0.4272	133.3333	6000	0.4059
0.4219	144.4444	6500	0.4058
0.4125	155.5556	7000	0.4049
0.42	166.6667	7500	0.4046
0.4145	177.7778	8000	0.4039

Framework versions

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