SpeechT5 TTS Nigerian English
This model is a fine-tuned version of microsoft/speecht5_tts on the Nigerian English TTS dataset. It achieves the following results on the evaluation set:
- Loss: 0.4957
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use 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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5928 | 17.5487 | 1000 | 0.5506 |
| 0.4771 | 35.0885 | 2000 | 0.4972 |
| 0.4376 | 52.6372 | 3000 | 0.4875 |
| 0.4249 | 70.1770 | 4000 | 0.4957 |
Framework versions
- Transformers 4.51.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1
- Downloads last month
- 8
Model tree for aljebra/speecht5_tts_nigerian_accent
Base model
microsoft/speecht5_tts