metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: finetuned_speecht5_50Kdata
results: []
finetuned_speecht5_50Kdata
This model is a fine-tuned version of microsoft/speecht5_tts on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3766
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: 3e-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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5055 | 0.3505 | 500 | 0.4585 |
| 0.4679 | 0.7010 | 1000 | 0.4248 |
| 0.4444 | 1.0515 | 1500 | 0.4140 |
| 0.4356 | 1.4020 | 2000 | 0.4109 |
| 0.434 | 1.7525 | 2500 | 0.4082 |
| 0.428 | 2.1030 | 3000 | 0.4023 |
| 0.423 | 2.4536 | 3500 | 0.4003 |
| 0.4177 | 2.8041 | 4000 | 0.3835 |
| 0.4077 | 3.1546 | 4500 | 0.3766 |
| 0.4096 | 3.5051 | 5000 | 0.3781 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.19.1