---
license: mit
tags:
- generated_from_trainer
datasets:
- common_voice_13_0
model-index:
- name: speecht5_finetuned_roman_ur
  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_finetuned_roman_ur

This model is a fine-tuned version of [EhsanElahi/speecht5_finetuned_voxpopuli_nl](https://huggingface.co/EhsanElahi/speecht5_finetuned_voxpopuli_nl) on the common_voice_13_0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4980

## 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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 1024
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 100

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.5267        | 13.56 | 50   | 0.4973          |
| 0.5245        | 27.12 | 100  | 0.4980          |


### Framework versions

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