wenxinkoh06/speecht5_tts

speecht5_tailo_Hokkien_ver1.0.a

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: 0.3882

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: 1
• 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: 400.0
• training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss
0.9773	0.5376	400	0.5568
0.5720	1.0753	800	0.4502
0.5098	1.6129	1200	0.4448
0.4776	2.1505	1600	0.4181
0.4564	2.6882	2000	0.4099
0.4461	3.2258	2400	0.4007
0.4391	3.7634	2800	0.3968
0.4353	4.3011	3200	0.3900
0.4296	4.8387	3600	0.3913
0.4254	5.3763	4000	0.3882

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2