speecht5-ljspeech-colab
This model is a fine-tuned version of microsoft/speecht5_tts on the lj_speech dataset. It achieves the following results on the evaluation set:
- Loss: 0.4033
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 8.3876 | 1.1778 | 100 | 0.4790 |
| 7.4738 | 2.3556 | 200 | 0.4167 |
| 7.2855 | 3.5333 | 300 | 0.4094 |
| 7.2444 | 4.7111 | 400 | 0.4061 |
| 7.2200 | 5.8889 | 500 | 0.4033 |
Framework versions
- Transformers 5.17.0
- Pytorch 2.11.0+cu128
- Datasets 3.6.0
- Tokenizers 0.23.1
- Downloads last month
- 15
Model tree for hsaim/speecht5-ljspeech-colab
Base model
microsoft/speecht5_tts