|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: microsoft/speecht5_tts |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: speecht5_finetuned_emirhan_tr |
|
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_finetuned_emirhan_tr |
|
|
|
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2990 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.5108 | 0.0571 | 100 | 0.4464 | |
|
| 0.42 | 0.1142 | 200 | 0.3574 | |
|
| 0.377 | 0.1713 | 300 | 0.3402 | |
|
| 0.3568 | 0.2284 | 400 | 0.3280 | |
|
| 0.3474 | 0.2855 | 500 | 0.3244 | |
|
| 0.3439 | 0.3426 | 600 | 0.3145 | |
|
| 0.3337 | 0.3997 | 700 | 0.3114 | |
|
| 0.3307 | 0.4568 | 800 | 0.3041 | |
|
| 0.3243 | 0.5140 | 900 | 0.3001 | |
|
| 0.3231 | 0.5711 | 1000 | 0.2990 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.1 |
|
- Pytorch 2.4.0 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.20.0 |
|
|
