| --- |
| language: |
| - tr |
| license: mit |
| base_model: microsoft/speecht5_tts |
| tags: |
| - text-to-speech |
| - turkish |
| - speech-generation |
| - generated_from_trainer |
| datasets: |
| - common_voice |
| model-index: |
| - name: SpeechT5 TTS Turkish |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # SpeechT5 TTS Turkish |
|
|
| This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the CommonVoice dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.4641 |
|
|
| ## 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 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:------:|:----:|:---------------:| |
| | 0.4707 | 111.11 | 1000 | 0.4559 | |
| | 0.4331 | 222.22 | 2000 | 0.4649 | |
| | 0.4162 | 333.33 | 3000 | 0.4610 | |
| | 0.4317 | 444.44 | 4000 | 0.4641 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.33.0.dev0 |
| - Pytorch 2.0.1+cu117 |
| - Datasets 2.14.4 |
| - Tokenizers 0.13.3 |
|
|
