---
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
datasets:
- lj_speech
model-index:
- name: speecht5_lj_speech
  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_lj_speech

This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the lj_speech dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7691

## 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: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 1000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.0568        | 1.3514 | 250  | 0.9258          |
| 0.885         | 2.7027 | 500  | 0.7979          |
| 0.8344        | 4.0541 | 750  | 0.7774          |
| 0.8389        | 5.4054 | 1000 | 0.7691          |


### Framework versions

- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1