You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
PaddleSpeech/demos/style_fs2/README.md

28 lines
1.4 KiB

3 years ago
# Style FastSpeech2
## Introduction
[FastSpeech2](https://arxiv.org/abs/2006.04558) is a classical acoustic model for Text-to-Speech synthesis, which introduces controllable speech input, including `phoneme duration`、`energy` and `pitch`.
3 years ago
In the prediction phase, you can change these controllable variables to get some interesting results.
For example:
1. The `duration` control in `FastSpeech2` can control the speed of audios will keep the `pitch`. (in some speech tool, increase the speed will increase the pitch, and vice versa.)
2. When we set `pitch` of one sentence to a mean value and set `tones` of phones to `1`, we will get a `robot-style` timbre.
3. When we raise the `pitch` of an adult female (with a fixed scale ratio), we will get a `child-style` timbre.
The `duration` and `pitch` of different phonemes in a sentence can have different scale ratios. You can set different scale ratios to emphasize or weaken the pronunciation of some phonemes.
## Usage
3 years ago
Run the following command line to get started:
```
./run.sh
```
3 years ago
In `run.sh`, it will execute `source path.sh` firstly, which will set the environment variants.
If you would like to try your own sentence, please replace the sentence in `sentences.txt`.
3 years ago
For more details, please see `style_syn.py`
3 years ago
The audio samples are in [style-control-in-fastspeech2](https://paddlespeech.readthedocs.io/en/latest/tts/demo.html#style-control-in-fastspeech2)