SpeechT5 TTS Kinyarwanda
This model is a fine-tuned version of microsoft/speecht5_tts on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4979
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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5633 | 2.4272 | 1000 | 0.5130 |
| 0.5464 | 4.8544 | 2000 | 0.5075 |
| 0.5336 | 7.2816 | 3000 | 0.4988 |
| 0.5334 | 9.7087 | 4000 | 0.4979 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 4
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.