speecht5_finetuned_griffin_ch_lu

This model is a fine-tuned version of microsoft/speecht5_tts on the SwissDial lucerne dialect. It achieves the following results on the evaluation set:

• Loss: 0.4034

Model description

Text-to-speech model for Luzern Swiss German dialect trained using SwissDial lucerne dialect samples.

Intended uses & limitations

A helper for learning Swiss German--though it does not perform well with single word phrases.

Training and evaluation data

SwissDial lucerne dialecct samples.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0001
• train_batch_size: 4
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH 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: 100
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5249	1.3142	100	0.4648
0.4782	2.6285	200	0.4286
0.4537	3.9427	300	0.4166
0.437	5.2619	400	0.4078
0.4268	6.5761	500	0.4034

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 2.14.4
• Tokenizers 0.21.2