---
library_name: transformers
license: mit
base_model: fahadqazi/Sindhi-TTS
tags:
- generated_from_trainer
model-index:
- name: Sindhi-TTS
  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. -->

# Sindhi-TTS

This model is a fine-tuned version of [fahadqazi/Sindhi-TTS](https://huggingface.co/fahadqazi/Sindhi-TTS) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2889

## 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: 8e-05
- train_batch_size: 8
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 |
|:-------------:|:-------:|:----:|:---------------:|
| 0.2993        | 2.5409  | 100  | 0.3057          |
| 0.295         | 5.0943  | 200  | 0.2967          |
| 0.3012        | 7.6352  | 300  | 0.2983          |
| 0.2945        | 10.1887 | 400  | 0.2988          |
| 0.2932        | 12.7296 | 500  | 0.2967          |
| 0.2911        | 15.2830 | 600  | 0.2925          |
| 0.2906        | 17.8239 | 700  | 0.2938          |
| 0.2931        | 20.3774 | 800  | 0.2927          |
| 0.2897        | 22.9182 | 900  | 0.2908          |
| 0.2972        | 25.4717 | 1000 | 0.2889          |


### Framework versions

- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3