Washere-1/speecht5_tts_kin

SpeechT5 TTS kinyarwanda

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

• Loss: 0.3370

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: 42
• gradient_accumulation_steps: 2
• 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: 500
• training_steps: 6000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.7933	12.3457	1000	0.3538
0.7485	24.6914	2000	0.3403
0.7305	37.0370	3000	0.3354
0.7253	49.3827	4000	0.3351
0.7231	61.7284	5000	0.3358
0.7144	74.0741	6000	0.3370

Framework versions

• Transformers 5.0.1.dev0
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.22.2