metadata
license: mit
base_model: MBZUAI/speecht5_tts_clartts_ar
tags:
- generated_from_trainer
model-index:
- name: speecht5_clartts_finetuned_TTS-PLS
results: []
speecht5_clartts_finetuned_TTS-PLS
This model is a fine-tuned version of MBZUAI/speecht5_tts_clartts_ar on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6020
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-06
- 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: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7089 | 2.8229 | 500 | 0.6678 |
| 0.6632 | 5.6457 | 1000 | 0.6319 |
| 0.6494 | 8.4686 | 1500 | 0.6162 |
| 0.6369 | 11.2915 | 2000 | 0.6099 |
| 0.6338 | 14.1143 | 2500 | 0.6067 |
| 0.6307 | 16.9372 | 3000 | 0.6023 |
| 0.6264 | 19.7601 | 3500 | 0.6031 |
| 0.628 | 22.5829 | 4000 | 0.6020 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1