olawale-ahmed/pidgin_speecht5_tts_google_waxal

SpeechT5 Waxal TTS Pidgin

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

• Loss: 0.4261

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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: 500
• training_steps: 3000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.9760	13.8889	1000	0.4434
0.9209	27.7778	2000	0.4302
0.9257	41.6667	3000	0.4261

Framework versions

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