README.md

---
tags:
- TensorFlowTTS
- audio
- text-to-speech
- text-to-mel
language: eng
license: apache-2.0
datasets:
- LJSpeech
widget:
- text: "How are you?"
---



This repository provides a pretrained [FastSpeech](https://arxiv.org/abs/1905.09263) trained on LJSpeech dataset (ENG). For a detail of the model, we encourage you to read more about
[TensorFlowTTS](https://github.com/TensorSpeech/TensorFlowTTS). 


## Install TensorFlowTTS
First of all, please install TensorFlowTTS with the following command:
```
pip install TensorFlowTTS
```

### Converting your Text to Mel Spectrogram
```python
import numpy as np
import soundfile as sf
import yaml

import tensorflow as tf

from tensorflow_tts.inference import AutoProcessor
from tensorflow_tts.inference import TFAutoModel

processor = AutoProcessor.from_pretrained("ruslanmv/tensorflowtts")
fastspeech = TFAutoModel.from_pretrained("ruslanmv/tensorflowtts")

text = "How are you?"

input_ids = processor.text_to_sequence(text)

mel_before, mel_after, duration_outputs = fastspeech.inference(
    input_ids=tf.expand_dims(tf.convert_to_tensor(input_ids, dtype=tf.int32), 0),
    speaker_ids=tf.convert_to_tensor([0], dtype=tf.int32),
    speed_ratios=tf.convert_to_tensor([1.0], dtype=tf.float32),
)
```