This model is a fine-tuned version of microsoft/speecht5_tts on the asr-nigerian-pidgin/nigerian-pidgin-1.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.4525

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_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: 5000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.0044	13.3333	1000	0.4587
0.9544	26.6667	2000	0.4492
0.9284	40.0	3000	0.4509
0.9336	53.3333	4000	0.4527
0.9006	66.6667	5000	0.4525

Framework versions

Transformers 5.0.0
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

olawale-ahmed/pidgin_speecht5_tts_nigerian-pidgin-1.0

SpeechT5 TTS Pidgin

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

olawale-ahmed/
pidgin_speecht5_tts_nigerian-pidgin-1.0