---
language:
- ckb
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_17_0
model-index:
- name: SpeechT5 TTS Kurdish - Sorani
  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. -->

# SpeechT5 TTS Kurdish - Sorani

This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the Mozilla Common Voice dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5069

## 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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- 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: 16000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step  | Validation Loss |
|:-------------:|:-------:|:-----:|:---------------:|
| 0.556         | 18.4332 | 4000  | 0.5184          |
| 0.5182        | 36.8664 | 8000  | 0.5033          |
| 0.5071        | 55.2995 | 12000 | 0.5057          |
| 0.5039        | 73.7327 | 16000 | 0.5069          |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.3.1+cu118
- Datasets 2.19.2
- Tokenizers 0.19.1