metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: speecht5_finetuned_PersianTTS
results: []
speecht5_finetuned_PersianTTS
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: 0.5380
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: 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: 500
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9582 | 0.1925 | 250 | 0.6677 |
| 0.6618 | 0.3851 | 500 | 0.5812 |
| 0.586 | 0.5776 | 750 | 0.5595 |
| 0.5617 | 0.7701 | 1000 | 0.5486 |
| 0.5547 | 0.9626 | 1250 | 0.5420 |
| 0.5429 | 1.1552 | 1500 | 0.5411 |
| 0.5372 | 1.3477 | 1750 | 0.5377 |
| 0.5365 | 1.5402 | 2000 | 0.5380 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1