metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: speecht5_finetuned_emirhan_tr
results: []
speecht5_finetuned_emirhan_tr
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: 0.2985
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- 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: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5079 | 0.4545 | 100 | 0.4190 |
| 0.4305 | 0.9091 | 200 | 0.3653 |
| 0.3847 | 1.3636 | 300 | 0.3456 |
| 0.3575 | 1.8182 | 400 | 0.3453 |
| 0.3482 | 2.2727 | 500 | 0.3231 |
| 0.3414 | 2.7273 | 600 | 0.3151 |
| 0.333 | 3.1818 | 700 | 0.3079 |
| 0.3254 | 3.6364 | 800 | 0.3021 |
| 0.3203 | 4.0909 | 900 | 0.2989 |
| 0.3174 | 4.5455 | 1000 | 0.2985 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0