metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: speecht5_finetuned_egypt_dialect
results: []
speecht5_finetuned_egypt_dialect
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: 0.4256
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- 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 |
|---|---|---|---|
| 0.5068 | 1.8265 | 100 | 0.4667 |
| 0.4739 | 3.6530 | 200 | 0.4497 |
| 0.4598 | 5.4795 | 300 | 0.4408 |
| 0.4574 | 7.3059 | 400 | 0.4326 |
| 0.4434 | 9.1324 | 500 | 0.4287 |
| 0.4403 | 10.9589 | 600 | 0.4260 |
| 0.4362 | 12.7854 | 700 | 0.4241 |
| 0.4291 | 14.6119 | 800 | 0.4228 |
| 0.4275 | 16.4384 | 900 | 0.4232 |
| 0.4256 | 18.2648 | 1000 | 0.4256 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1