speecht5_tts_lg
This model is a fine-tuned version of microsoft/speecht5_tts on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3654
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: 8
- eval_batch_size: 24
- seed: 42
- gradient_accumulation_steps: 4
- 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 |
---|---|---|---|
0.4208 | 14.81 | 1000 | 0.3788 |
0.3912 | 29.63 | 2000 | 0.3669 |
0.3901 | 44.44 | 3000 | 0.3646 |
0.3893 | 59.26 | 4000 | 0.3654 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
- Downloads last month
- 29
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for EricPeter/speecht5_tts_lg
Base model
microsoft/speecht5_tts