SpeechT5-TTS-Nepali-SLR43-SLR143-SWOS
This model is a fine-tuned version of aryamanstha/speecht5_nepali_oslr43_oslr143 on the swos dataset. It achieves the following results on the evaluation set:
- Loss: 0.4827
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: 128
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 418
- training_steps: 2615
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.4978 | 37.04 | 1000 | 0.4787 |
0.4742 | 74.07 | 2000 | 0.4827 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.13.3
- Downloads last month
- 3