---
language:
- en
license: mit
base_model: microsoft/speecht5_tts
tags:
- en_accent,vocpopuli,t5
- generated_from_trainer
datasets:
- facebook/voxpopuli
model-index:
- name: SpeechT5 TTS English Accented
  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 English Accented

This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the VoxPopuli dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6988

## 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: 6
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 12
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.4211        | 222.22 | 1000 | 0.6265          |
| 0.4094        | 444.44 | 2000 | 0.6595          |
| 0.3729        | 666.67 | 3000 | 0.7037          |
| 0.365         | 888.89 | 4000 | 0.6988          |


### Framework versions

- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1