metadata
library_name: transformers
license: mit
base_model: MBZUAI/speecht5_tts_clartts_ar
tags:
- generated_from_trainer
datasets:
- fleurs
model-index:
- name: speecht5_sindhi
results: []
speecht5_sindhi
This model is a fine-tuned version of MBZUAI/speecht5_tts_clartts_ar on the fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.4007
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- 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 |
|---|---|---|---|
| 0.4691 | 2.5974 | 100 | 0.4582 |
| 0.4505 | 5.1948 | 200 | 0.4339 |
| 0.4399 | 7.7922 | 300 | 0.4288 |
| 0.4277 | 10.3896 | 400 | 0.4193 |
| 0.4188 | 12.9870 | 500 | 0.4128 |
| 0.4111 | 15.5844 | 600 | 0.4041 |
| 0.4085 | 18.1818 | 700 | 0.4025 |
| 0.4033 | 20.7792 | 800 | 0.4005 |
| 0.3992 | 23.3766 | 900 | 0.4000 |
| 0.399 | 25.9740 | 1000 | 0.4007 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1