senga-nt-asr-inferred-force-aligned-speecht5-LUK-ACT

This model is a fine-tuned version of microsoft/speecht5_tts on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5318

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: 8
• eval_batch_size: 8
• seed: 3407
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• 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: 200
• num_epochs: 300.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5415	29.4148	1000	0.5518
0.4976	58.8296	2000	0.5369
0.4763	88.2370	3000	0.5323
0.4762	117.6519	4000	0.5341
0.4607	147.0593	5000	0.5326
0.4497	176.4741	6000	0.5361
0.4489	205.8889	7000	0.5325
0.4346	235.2963	8000	0.5331
0.4373	264.7111	9000	0.5312
0.4393	294.1185	10000	0.5318

Framework versions

• Transformers 4.57.1
• Pytorch 2.8.0+cu128
• Datasets 4.2.0
• Tokenizers 0.22.1