|
|
@ -1,3 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
# TTS(Text To Speech)
|
|
|
|
# TTS(Text To Speech)
|
|
|
|
|
|
|
|
|
|
|
|
## Introduction
|
|
|
|
## Introduction
|
|
|
@ -13,15 +14,35 @@ pip install paddlespeech
|
|
|
|
|
|
|
|
|
|
|
|
### 2. Prepare Input
|
|
|
|
### 2. Prepare Input
|
|
|
|
Input of this demo should be a text of the specific language that can be passed via argument.
|
|
|
|
Input of this demo should be a text of the specific language that can be passed via argument.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
### 3. Usage
|
|
|
|
### 3. Usage
|
|
|
|
- Command Line(Recommended)
|
|
|
|
- Command Line (Recommended)
|
|
|
|
|
|
|
|
- Chinese
|
|
|
|
|
|
|
|
```bash
|
|
|
|
|
|
|
|
paddlespeech tts --input "你好,欢迎使用百度飞桨深度学习框架!"
|
|
|
|
|
|
|
|
```
|
|
|
|
|
|
|
|
The default acoustic model is `Fastspeech2`, and the default vocoder is `Parallel WaveGAN`.
|
|
|
|
|
|
|
|
- Chinese, use `SpeedySpeech` as acoustic model
|
|
|
|
|
|
|
|
```bash
|
|
|
|
|
|
|
|
paddlespeech tts --am speedyspeech_csmsc --input "你好,欢迎使用百度飞桨深度学习框架!"
|
|
|
|
|
|
|
|
```
|
|
|
|
|
|
|
|
- Chinese, multi speaker
|
|
|
|
```bash
|
|
|
|
```bash
|
|
|
|
paddlespeech tts --input 今天的天气不错啊
|
|
|
|
paddlespeech tts --am fastspeech2_aishell3 --voc pwgan_aishell3 --input "你好,欢迎使用百度飞桨深度学习框架!" --spk_id 0
|
|
|
|
```
|
|
|
|
```
|
|
|
|
Usage:
|
|
|
|
You can change `spk_id` here.
|
|
|
|
|
|
|
|
- English
|
|
|
|
```bash
|
|
|
|
```bash
|
|
|
|
|
|
|
|
paddlespeech tts --am fastspeech2_ljspeech --voc pwgan_ljspeech --lang en --input "hello world"
|
|
|
|
|
|
|
|
```
|
|
|
|
|
|
|
|
- English, multi speaker
|
|
|
|
|
|
|
|
```bash
|
|
|
|
|
|
|
|
paddlespeech tts --am fastspeech2_vctk --voc pwgan_vctk --input "hello, boys" --lang en --spk_id 0
|
|
|
|
|
|
|
|
```
|
|
|
|
|
|
|
|
You can change `spk_id` here.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
- Usage:
|
|
|
|
|
|
|
|
```bash
|
|
|
|
paddlespeech tts --help
|
|
|
|
paddlespeech tts --help
|
|
|
|
```
|
|
|
|
```
|
|
|
|
Arguments:
|
|
|
|
Arguments:
|
|
|
@ -79,7 +100,7 @@ Input of this demo should be a text of the specific language that can be passed
|
|
|
|
```
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
### 4.Pretrained Models
|
|
|
|
### 4. Pretrained Models
|
|
|
|
|
|
|
|
|
|
|
|
Here is a list of pretrained models released by PaddleSpeech that can be used by command and python api:
|
|
|
|
Here is a list of pretrained models released by PaddleSpeech that can be used by command and python api:
|
|
|
|
|
|
|
|
|
|
|
|