speecht5_tailo_Hokkien_ver1.0.c

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: 0.3215

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: 3e-05
• train_batch_size: 8
• eval_batch_size: 16
• 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: 6000.0
• training_steps: 54000

Training results

Training Loss	Epoch	Step	Validation Loss
0.4004	0.8743	6000	0.3637
0.3821	1.7485	12000	0.3519
0.3673	2.6228	18000	0.3422
0.3594	3.4970	24000	0.3331
0.3540	4.3713	30000	0.3303
0.3493	5.2455	36000	0.3276
0.3459	6.1198	42000	0.3251
0.3434	6.9940	48000	0.3230
0.3418	7.8683	54000	0.3215

Framework versions

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