speecht5_finetuned_swahili

This model is a fine-tuned version of microsoft/speecht5_tts on the A kiswahili Dataset for Development of Text-To-Speech System dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.4618
• eval_runtime: 11.2006
• eval_samples_per_second: 54.015
• eval_steps_per_second: 27.052
• epoch: 11.76
• step: 2000

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: 4
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.13.3