---
license: mit
tags:
- generated_from_trainer
datasets:
- voxpopuli
model-index:
- name: speecht5_finetuned_voxpopuli_it_partial
  results: []
pipeline_tag: text-to-speech
---

<!-- 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_finetuned_voxpopuli_it_partial

This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on a part of the italian voxpopuli dataset.
It was finetuned as part of the HF Audio Course.

It achieves the following results on the evaluation set:
- Loss: 0.4955

## 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: 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: 3000

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.5461        | 17.39 | 1000 | 0.5055          |
| 0.5222        | 34.78 | 2000 | 0.4958          |
| 0.5125        | 52.17 | 3000 | 0.4955          |


### Framework versions

- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3