senga-nt-asr-inferred-force-aligned-speecht5-MAT-ms-mel

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: 0.0818

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: cosine
• lr_scheduler_warmup_steps: 200
• num_epochs: 600.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.0836	58.8485	1000	0.0729
0.0719	117.6667	2000	0.0760
0.0618	176.4848	3000	0.0772
0.0577	235.3030	4000	0.0794
0.0555	294.1212	5000	0.0799
0.0545	352.9697	6000	0.0798
0.0514	411.7879	7000	0.0817
0.048	470.6061	8000	0.0826
0.0505	529.4242	9000	0.0817
0.0492	588.2424	10000	0.0818

Framework versions

• Transformers 4.57.1
• Pytorch 2.8.0+cu128
• Datasets 4.2.0
• Tokenizers 0.22.2