SpeechT5 TTS Assamese
This model is a fine-tuned version of microsoft/speecht5_tts on the Assamese Speech Corpus dataset. It achieves the following results on the evaluation set:
- Loss: 0.3736
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 250
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5354 | 4.7619 | 200 | 0.4629 |
| 0.4494 | 9.5238 | 400 | 0.3915 |
| 0.4326 | 14.2857 | 600 | 0.3822 |
| 0.4275 | 19.0476 | 800 | 0.3761 |
| 0.4188 | 23.8095 | 1000 | 0.3736 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 2