README.md 28.5 KB
Newer Older
G
grasswolfs 已提交
1 2
([简体中文](./README_cn.md)|English)

M
Mingxue-Xu 已提交
3
<p align="center">
M
Mingxue-Xu 已提交
4
  <img src="./docs/images/PaddleSpeech_logo.png" />
M
Mingxue-Xu 已提交
5 6 7 8 9
</p>
<div align="center">  

  <h3>
  <a href="#quick-start"> Quick Start </a>
L
lym0302 已提交
10
  | <a href="#quick-start-server"> Quick Start Server </a>
M
Mingxue-Xu 已提交
11
  | <a href="#documents"> Documents </a>
Z
Zeyu Chen 已提交
12
  | <a href="#model-list"> Models List </a>
M
Mingxue-Xu 已提交
13 14 15
</div>

------------------------------------------------------------------------------------
Z
Zeyu Chen 已提交
16

G
grasswolfs 已提交
17 18

<p align="center">
小湉湉's avatar
小湉湉 已提交
19
    <a href="./LICENSE"><img src="https://img.shields.io/badge/license-Apache%202-red.svg"></a>
H
Hui Zhang 已提交
20 21
    <a href="https://github.com/PaddlePaddle/PaddleSpeech/releases"><img src="https://img.shields.io/github/v/release/PaddlePaddle/PaddleSpeech?color=ffa"></a>
    <a href="support os"><img src="https://img.shields.io/badge/os-linux%2C%20win%2C%20mac-pink.svg"></a>
小湉湉's avatar
小湉湉 已提交
22 23 24
    <a href=""><img src="https://img.shields.io/badge/python-3.7+-aff.svg"></a>
    <a href="https://github.com/PaddlePaddle/PaddleSpeech/graphs/contributors"><img src="https://img.shields.io/github/contributors/PaddlePaddle/PaddleSpeech?color=9ea"></a>
    <a href="https://github.com/PaddlePaddle/PaddleSpeech/commits"><img src="https://img.shields.io/github/commit-activity/m/PaddlePaddle/PaddleSpeech?color=3af"></a>
G
grasswolfs 已提交
25 26
    <a href="https://github.com/PaddlePaddle/PaddleSpeech/issues"><img src="https://img.shields.io/github/issues/PaddlePaddle/PaddleSpeech?color=9cc"></a>
    <a href="https://github.com/PaddlePaddle/PaddleSpeech/stargazers"><img src="https://img.shields.io/github/stars/PaddlePaddle/PaddleSpeech?color=ccf"></a>
H
Hui Zhang 已提交
27 28
    <a href="=https://pypi.org/project/paddlespeech/"><img src="https://img.shields.io/pypi/dm/PaddleSpeech"></a>
    <a href="=https://pypi.org/project/paddlespeech/"><img src="https://static.pepy.tech/badge/paddlespeech"></a>
D
DanielYang 已提交
29
    <a href="https://huggingface.co/spaces"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue"></a>
G
grasswolfs 已提交
30
</p>
L
lfchener 已提交
31

M
Mingxue-Xu 已提交
32

33
**PaddleSpeech** is an open-source toolkit on [PaddlePaddle](https://github.com/PaddlePaddle/Paddle) platform for a variety of critical tasks in speech and audio, with the state-of-art and influential models.
M
Mingxue-Xu 已提交
34

H
Hui Zhang 已提交
35
##### Speech Recognition
M
Mingxue-Xu 已提交
36 37 38 39 40 41

<div align = "center">
<table style="width:100%">
  <thead>
    <tr>
      <th> Input Audio  </th>
M
Mingxue-Xu 已提交
42
      <th width="550"> Recognition Result  </th>
M
Mingxue-Xu 已提交
43 44 45 46 47
    </tr>
  </thead>
  <tbody>
   <tr>
      <td align = "center">
M
Mingxue-Xu 已提交
48
      <a href="https://paddlespeech.bj.bcebos.com/PaddleAudio/en.wav" rel="nofollow">
M
Mingxue-Xu 已提交
49
            <img align="center" src="./docs/images/audio_icon.png" width="200 style="max-width: 100%;"></a><br>
M
Mingxue-Xu 已提交
50
      </td>
M
Mingxue-Xu 已提交
51
      <td >I knocked at the door on the ancient side of the building.</td>
M
Mingxue-Xu 已提交
52 53 54
    </tr>
    <tr>
      <td align = "center">
M
Mingxue-Xu 已提交
55
      <a href="https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav" rel="nofollow">
M
Mingxue-Xu 已提交
56
            <img align="center" src="./docs/images/audio_icon.png" width="200" style="max-width: 100%;"></a><br>
M
Mingxue-Xu 已提交
57
      </td>
M
Mingxue-Xu 已提交
58
      <td>我认为跑步最重要的就是给我带来了身体健康。</td>
M
Mingxue-Xu 已提交
59
    </tr>
M
Mingxue-Xu 已提交
60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82
  </tbody>
</table>

</div>

##### Speech Translation (English to Chinese)

<div align = "center">
<table style="width:100%">
  <thead>
    <tr>
      <th> Input Audio  </th>
      <th width="550"> Translations Result  </th>
    </tr>
  </thead>
  <tbody>
   <tr>
      <td align = "center">
      <a href="https://paddlespeech.bj.bcebos.com/PaddleAudio/en.wav" rel="nofollow">
            <img align="center" src="./docs/images/audio_icon.png" width="200 style="max-width: 100%;"></a><br>
      </td>
      <td >我 在 这栋 建筑 的 古老 门上 敲门。</td>
    </tr>
M
Mingxue-Xu 已提交
83 84 85 86
  </tbody>
</table>

</div>
87

Z
Zeyu Chen 已提交
88
##### Text-to-Speech
M
Mingxue-Xu 已提交
89 90 91 92
<div align = "center">
<table style="width:100%">
  <thead>
    <tr>
小湉湉's avatar
小湉湉 已提交
93
      <th width="550" > Input Text</th>
M
Mingxue-Xu 已提交
94 95 96 97 98 99 100
      <th>Synthetic Audio</th>
    </tr>
  </thead>
  <tbody>
   <tr>
      <td >Life was like a box of chocolates, you never know what you're gonna get.</td>
      <td align = "center">
小湉湉's avatar
小湉湉 已提交
101
      <a href="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/tacotron2_ljspeech_waveflow_samples_0.2/sentence_1.wav" rel="nofollow">
M
Mingxue-Xu 已提交
102 103 104 105 106 107 108 109 110 111
            <img align="center" src="./docs/images/audio_icon.png" width="200" style="max-width: 100%;"></a><br>
      </td>
    </tr>
    <tr>
      <td >早上好,今天是2020/10/29,最低温度是-3°C。</td>
      <td align = "center">
      <a href="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/001.wav" rel="nofollow">
            <img align="center" src="./docs/images/audio_icon.png" width="200" style="max-width: 100%;"></a><br>
      </td>
    </tr>
小湉湉's avatar
小湉湉 已提交
112 113 114 115 116 117 118
    <tr>
      <td >季姬寂,集鸡,鸡即棘鸡。棘鸡饥叽,季姬及箕稷济鸡。鸡既济,跻姬笈,季姬忌,急咭鸡,鸡急,继圾几,季姬急,即籍箕击鸡,箕疾击几伎,伎即齑,鸡叽集几基,季姬急极屐击鸡,鸡既殛,季姬激,即记《季姬击鸡记》。</td>
      <td align = "center">
      <a href="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/jijiji.wav" rel="nofollow">
            <img align="center" src="./docs/images/audio_icon.png" width="200" style="max-width: 100%;"></a><br>
      </td>
    </tr>
M
Mingxue-Xu 已提交
119 120 121 122 123
  </tbody>
</table>

</div>

Z
Zeyu Chen 已提交
124
For more synthesized audios, please refer to [PaddleSpeech Text-to-Speech samples](https://paddlespeech.readthedocs.io/en/latest/tts/demo.html).
小湉湉's avatar
小湉湉 已提交
125

小湉湉's avatar
小湉湉 已提交
126
##### Punctuation Restoration
K
KP 已提交
127 128 129 130
<div align = "center">
<table style="width:100%">
  <thead>
    <tr>
小湉湉's avatar
小湉湉 已提交
131 132
      <th width="390"> Input Text </th>
      <th width="390"> Output Text </th>
K
KP 已提交
133 134 135 136 137 138 139 140 141 142 143 144
    </tr>
  </thead>
  <tbody>
   <tr>
      <td>今天的天气真不错啊你下午有空吗我想约你一起去吃饭</td>
      <td>今天的天气真不错啊!你下午有空吗?我想约你一起去吃饭。</td>
    </tr>
  </tbody>
</table>

</div>

145 146 147 148 149
### ⭐ Examples
- **[PaddleBoBo](https://github.com/JiehangXie/PaddleBoBo): Use PaddleSpeech TTS to generate virtual human voice.**
  
<div align="center"><a href="https://www.bilibili.com/video/BV1cL411V71o?share_source=copy_web"><img src="https://ai-studio-static-online.cdn.bcebos.com/06fd746ab32042f398fb6f33f873e6869e846fe63c214596ae37860fe8103720" / width="500px"></a></div>

小湉湉's avatar
小湉湉 已提交
150
- [PaddleSpeech Demo Video](https://paddlespeech.readthedocs.io/en/latest/demo_video.html)
151

J
Jerryuhoo 已提交
152
- **[VTuberTalk](https://github.com/jerryuhoo/VTuberTalk): Use PaddleSpeech TTS and ASR to clone voice from videos.**
J
Jerryuhoo 已提交
153 154 155 156 157

<div align="center">
<img src="https://raw.githubusercontent.com/jerryuhoo/VTuberTalk/main/gui/gui.png"  width = "500px"  />
</div>

158 159 160 161 162 163 164 165 166
### 🔥 Hot Activities

- 2021.12.21~12.24

  4 Days Live Courses: Depth interpretation of PaddleSpeech!

  **Courses videos and related materials: https://aistudio.baidu.com/aistudio/education/group/info/25130**

### Features
167

M
Mingxue-Xu 已提交
168
Via the easy-to-use, efficient, flexible and scalable implementation, our vision is to empower both industrial application and academic research, including training, inference & testing modules, and deployment process. To be more specific, this toolkit features at:
小湉湉's avatar
小湉湉 已提交
169 170 171
- 📦  **Ease of Use**: low barriers to install, and [CLI](#quick-start) is available to quick-start your journey.
- 🏆  **Align to the State-of-the-Art**: we provide high-speed and ultra-lightweight models, and also cutting-edge technology. 
- 💯  **Rule-based Chinese frontend**: our frontend contains Text Normalization and Grapheme-to-Phoneme (G2P, including Polyphone and Tone Sandhi). Moreover, we use self-defined linguistic rules to adapt Chinese context.
M
Mingxue-Xu 已提交
172
- **Varieties of Functions that Vitalize both Industrial and Academia**:
小湉湉's avatar
小湉湉 已提交
173 174 175
  - 🛎️  *Implementation of critical audio tasks*: this toolkit contains audio functions like  Audio Classification, Speech Translation, Automatic Speech Recognition, Text-to-Speech Synthesis, etc.
  - 🔬  *Integration of mainstream models and datasets*: the toolkit implements modules that participate in the whole pipeline of the speech tasks, and uses mainstream datasets like LibriSpeech, LJSpeech, AIShell, CSMSC, etc. See also [model list](#model-list) for more details.
  - 🧩  *Cascaded models application*: as an extension of the typical traditional audio tasks, we combine the workflows of the aforementioned tasks with other fields like Natural language processing (NLP) and Computer Vision (CV).
M
Mingxue-Xu 已提交
176

177
### Recent Update
M
Mingxue-Xu 已提交
178 179 180 181

<!---
2021.12.14: We would like to have an online courses to introduce basics and research of speech, as well as code practice with `paddlespeech`. Please pay attention to our [Calendar](https://www.paddlepaddle.org.cn/live).
--->
H
Hui Zhang 已提交
182
- 👏🏻  2022.03.28: PaddleSpeech Server is available for Audio Classification, Automatic Speech Recognition and Text-to-Speech.
H
Hui Zhang 已提交
183
- 👏🏻  2022.03.28: PaddleSpeech CLI is available for Speaker Verification.
H
Hui Zhang 已提交
184
- 🤗  2021.12.14: Our PaddleSpeech [ASR](https://huggingface.co/spaces/KPatrick/PaddleSpeechASR) and [TTS](https://huggingface.co/spaces/KPatrick/PaddleSpeechTTS) Demos on Hugging Face Spaces are available!
小湉湉's avatar
小湉湉 已提交
185
- 👏🏻  2021.12.10: PaddleSpeech CLI is available for Audio Classification, Automatic Speech Recognition, Speech Translation (English to Chinese) and Text-to-Speech.
M
Mingxue-Xu 已提交
186

G
grasswolfs 已提交
187
### Community
小湉湉's avatar
小湉湉 已提交
188
- Scan the QR code below with your Wechat (reply【语音】after your friend's application is approved), you can access to official technical exchange group. Look forward to your participation.
M
Mingxue-Xu 已提交
189 190

<div align="center">
小湉湉's avatar
小湉湉 已提交
191
<img src="https://raw.githubusercontent.com/yt605155624/lanceTest/main/images/wechat_4.jpg"  width = "300"  />
M
Mingxue-Xu 已提交
192 193
</div>

Z
Zeyu Chen 已提交
194
## Installation
M
Mingxue-Xu 已提交
195

J
Jackwaterveg 已提交
196 197
We strongly recommend our users to install PaddleSpeech in **Linux** with *python>=3.7*.
Up to now, **Linux** supports CLI for the all our tasks, **Mac OSX** and **Windows** only supports PaddleSpeech CLI for Audio Classification, Speech-to-Text and Text-to-Speech. To install `PaddleSpeech`, please see [installation](./docs/source/install.md).
M
Mingxue-Xu 已提交
198

G
grasswolfs 已提交
199
<a name="quickstart"></a>
Z
Zeyu Chen 已提交
200
## Quick Start
M
Mingxue-Xu 已提交
201

M
Mingxue-Xu 已提交
202
Developers can have a try of our models with [PaddleSpeech Command Line](./paddlespeech/cli/README.md). Change `--input` to test your own audio/text.
M
Mingxue-Xu 已提交
203

M
Mingxue-Xu 已提交
204
**Audio Classification**     
M
Mingxue-Xu 已提交
205
```shell
小湉湉's avatar
小湉湉 已提交
206
paddlespeech cls --input input.wav
M
Mingxue-Xu 已提交
207
```
H
Hui Zhang 已提交
208

209 210 211 212 213
**Speaker Verification**
```
paddlespeech vector --task spk --input input_16k.wav
```

M
Mingxue-Xu 已提交
214 215
**Automatic Speech Recognition**
```shell
小湉湉's avatar
小湉湉 已提交
216
paddlespeech asr --lang zh --input input_16k.wav
M
Mingxue-Xu 已提交
217
```
H
Hui Zhang 已提交
218
- web demo for Automatic Speech Recognition is integrated to [Huggingface Spaces](https://huggingface.co/spaces) with [Gradio](https://github.com/gradio-app/gradio). See Demo: [ASR Demo](https://huggingface.co/spaces/KPatrick/PaddleSpeechASR)
小湉湉's avatar
小湉湉 已提交
219

H
Hui Zhang 已提交
220
**Speech Translation** (English to Chinese)
H
huangyuxin 已提交
221
(not support for Mac and Windows now)
M
Mingxue-Xu 已提交
222
```shell
小湉湉's avatar
小湉湉 已提交
223
paddlespeech st --input input_16k.wav
M
Mingxue-Xu 已提交
224
```
H
Hui Zhang 已提交
225

M
Mingxue-Xu 已提交
226
**Text-to-Speech** 
M
Mingxue-Xu 已提交
227
```shell
G
grasswolfs 已提交
228
paddlespeech tts --input "你好,欢迎使用飞桨深度学习框架!" --output output.wav
M
Mingxue-Xu 已提交
229
```
H
Hui Zhang 已提交
230
- web demo for Text to Speech is integrated to [Huggingface Spaces](https://huggingface.co/spaces) with [Gradio](https://github.com/gradio-app/gradio). See Demo: [TTS Demo](https://huggingface.co/spaces/KPatrick/PaddleSpeechTTS)
K
KP 已提交
231 232 233 234 235 236 237

**Text Postprocessing** 
- Punctuation Restoration
  ```bash
  paddlespeech text --task punc --input 今天的天气真不错啊你下午有空吗我想约你一起去吃饭
  ```

H
Hui Zhang 已提交
238 239 240 241 242
**Batch Process**
```
echo -e "1 欢迎光临。\n2 谢谢惠顾。" | paddlespeech tts
```  

H
Hui Zhang 已提交
243 244
**Shell Pipeline**   
- ASR + Punctuation Restoration
H
Hui Zhang 已提交
245 246 247
```
paddlespeech asr --input ./zh.wav | paddlespeech text --task punc
```
小湉湉's avatar
小湉湉 已提交
248 249 250

For more command lines, please see: [demos](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/demos)

251
If you want to try more functions like training and tuning, please have a look at [Speech-to-Text Quick Start](./docs/source/asr/quick_start.md) and [Text-to-Speech Quick Start](./docs/source/tts/quick_start.md).
Z
Zeyu Chen 已提交
252

L
lym0302 已提交
253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282

<a name="quickstartserver"></a>
## Quick Start Server

Developers can have a try of our speech server with [PaddleSpeech Server Command Line](./paddlespeech/server/README.md).

**Start server**     
```shell
paddlespeech_server start --config_file ./paddlespeech/server/conf/application.yaml
```

**Access Speech Recognition Services**     
```shell
paddlespeech_client asr --server_ip 127.0.0.1 --port 8090 --input input_16k.wav
```

**Access Text to Speech Services**     
```shell
paddlespeech_client tts --server_ip 127.0.0.1 --port 8090 --input "您好,欢迎使用百度飞桨语音合成服务。" --output output.wav
```

**Access Audio Classification Services**     
```shell
paddlespeech_client cls --server_ip 127.0.0.1 --port 8090 --input input.wav
```


For more information about server command lines, please see: [speech server demos](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/demos/speech_server)


I
iftaken 已提交
283 284
<a name="ModelList"></a>

Z
Zeyu Chen 已提交
285
## Model List
286

287
PaddleSpeech supports a series of most popular models. They are summarized in [released models](./docs/source/released_model.md) and attached with available pretrained models.
Z
Zeyu Chen 已提交
288

I
iftaken 已提交
289 290
<a name="SpeechToText"></a>

小湉湉's avatar
小湉湉 已提交
291
**Speech-to-Text** contains *Acoustic Model*, *Language Model*, and *Speech Translation*, with the following details:
L
lfchener 已提交
292

M
Mingxue-Xu 已提交
293 294 295
<table style="width:100%">
  <thead>
    <tr>
Z
Zeyu Chen 已提交
296
      <th>Speech-to-Text Module Type</th>
M
Mingxue-Xu 已提交
297 298 299 300 301 302 303
      <th>Dataset</th>
      <th>Model Type</th>
      <th>Link</th>
    </tr>
  </thead>
  <tbody>
    <tr>
小湉湉's avatar
小湉湉 已提交
304
      <td rowspan="4">Speech Recogination</td>
M
Mingxue-Xu 已提交
305 306 307
      <td rowspan="2" >Aishell</td>
      <td >DeepSpeech2 RNN + Conv based Models</td>
      <td>
H
Hui Zhang 已提交
308
      <a href = "./examples/aishell/asr0">deepspeech2-aishell</a>
M
Mingxue-Xu 已提交
309 310 311 312 313
      </td>
    </tr>
    <tr>
      <td>Transformer based Attention Models </td>
      <td>
H
Hui Zhang 已提交
314
      <a href = "./examples/aishell/asr1">u2.transformer.conformer-aishell</a>
M
Mingxue-Xu 已提交
315 316
      </td>
    </tr>
小湉湉's avatar
小湉湉 已提交
317
    <tr>
M
Mingxue-Xu 已提交
318 319 320
      <td> Librispeech</td>
      <td>Transformer based Attention Models </td>
      <td>
H
Hui Zhang 已提交
321
      <a href = "./examples/librispeech/asr0">deepspeech2-librispeech</a> / <a href = "./examples/librispeech/asr1">transformer.conformer.u2-librispeech</a>  / <a href = "./examples/librispeech/asr2">transformer.conformer.u2-kaldi-librispeech</a>
M
Mingxue-Xu 已提交
322 323 324
      </td>
      </td>
    </tr>
小湉湉's avatar
小湉湉 已提交
325 326 327 328 329 330 331
  <tr>
      <td>TIMIT</td>
      <td>Unified Streaming & Non-streaming Two-pass</td>
      <td>
    <a href = "./examples/timit/asr1"> u2-timit</a>
      </td>
  </tr>
M
Mingxue-Xu 已提交
332 333 334 335 336
  <tr>
  <td>Alignment</td>
  <td>THCHS30</td>
  <td>MFA</td>
  <td>
H
Hui Zhang 已提交
337
  <a href = ".examples/thchs30/align0">mfa-thchs30</a>
M
Mingxue-Xu 已提交
338 339
  </td>
  </tr>
M
Mingxue-Xu 已提交
340
   <tr>
小湉湉's avatar
小湉湉 已提交
341
      <td rowspan="1">Language Model</td>
M
Mingxue-Xu 已提交
342
      <td colspan = "2">Ngram Language Model</td>
M
Mingxue-Xu 已提交
343
      <td>
M
Mingxue-Xu 已提交
344
      <a href = "./examples/other/ngram_lm">kenlm</a>
M
Mingxue-Xu 已提交
345 346
      </td>
    </tr>
小湉湉's avatar
小湉湉 已提交
347
  <tr>
M
Mingxue-Xu 已提交
348 349 350 351 352 353 354 355 356 357 358 359 360
      <td rowspan="2">Speech Translation (English to Chinese)</td> 
      <td rowspan="2">TED En-Zh</td>
      <td>Transformer + ASR MTL</td>
      <td>
      <a href = "./examples/ted_en_zh/st0">transformer-ted</a>
      </td>
  </tr>
  <tr>
      <td>FAT + Transformer + ASR MTL</td>
      <td>
      <a href = "./examples/ted_en_zh/st1">fat-st-ted</a>
      </td>
  </tr>
M
Mingxue-Xu 已提交
361 362
  </tbody>
</table>
H
Hui Zhang 已提交
363

I
iftaken 已提交
364 365
<a name="TextToSpeech"></a>

366
**Text-to-Speech** in PaddleSpeech mainly contains three modules: *Text Frontend*, *Acoustic Model* and *Vocoder*. Acoustic Model and Vocoder models are listed as follow:
H
Hui Zhang 已提交
367

M
Mingxue-Xu 已提交
368 369 370
<table>
  <thead>
    <tr>
小湉湉's avatar
小湉湉 已提交
371 372 373 374
      <th> Text-to-Speech Module Type </th>
      <th> Model Type </th>
      <th> Dataset </th>
      <th> Link </th>
M
Mingxue-Xu 已提交
375 376 377 378
    </tr>
  </thead>
  <tbody>
    <tr>
小湉湉's avatar
小湉湉 已提交
379
    <td> Text Frontend </td>
M
Mingxue-Xu 已提交
380 381
    <td colspan="2"> &emsp; </td>
    <td>
382
    <a href = "./examples/other/tn">tn</a> / <a href = "./examples/other/g2p">g2p</a>
M
Mingxue-Xu 已提交
383 384 385 386
    </td>
    </tr>
    <tr>
      <td rowspan="4">Acoustic Model</td>
小湉湉's avatar
小湉湉 已提交
387 388
      <td>Tacotron2</td>
      <td>LJSpeech / CSMSC</td>
M
Mingxue-Xu 已提交
389
      <td>
小湉湉's avatar
小湉湉 已提交
390
      <a href = "./examples/ljspeech/tts0">tacotron2-ljspeech</a> / <a href = "./examples/csmsc/tts0">tacotron2-csmsc</a>
M
Mingxue-Xu 已提交
391 392 393
      </td>
    </tr>
    <tr>
小湉湉's avatar
小湉湉 已提交
394
      <td>Transformer TTS</td>
小湉湉's avatar
小湉湉 已提交
395
      <td>LJSpeech</td>
M
Mingxue-Xu 已提交
396 397 398 399 400 401 402 403 404 405 406 407 408
      <td>
      <a href = "./examples/ljspeech/tts1">transformer-ljspeech</a>
      </td>
    </tr>
    <tr>
      <td>SpeedySpeech</td>
      <td>CSMSC</td>
      <td >
      <a href = "./examples/csmsc/tts2">speedyspeech-csmsc</a>
      </td>
    </tr>
    <tr>
      <td>FastSpeech2</td>
小湉湉's avatar
小湉湉 已提交
409
      <td>LJSpeech / VCTK / CSMSC / AISHELL-3</td>
M
Mingxue-Xu 已提交
410
      <td>
小湉湉's avatar
小湉湉 已提交
411
      <a href = "./examples/ljspeech/tts3">fastspeech2-ljspeech</a> / <a href = "./examples/vctk/tts3">fastspeech2-vctk</a> / <a href = "./examples/csmsc/tts3">fastspeech2-csmsc</a> / <a href = "./examples/aishell3/tts3">fastspeech2-aishell3</a>
M
Mingxue-Xu 已提交
412 413 414
      </td>
    </tr>
   <tr>
小湉湉's avatar
小湉湉 已提交
415
      <td rowspan="6">Vocoder</td>
M
Mingxue-Xu 已提交
416 417 418 419 420 421 422 423
      <td >WaveFlow</td>
      <td >LJSpeech</td>
      <td>
      <a href = "./examples/ljspeech/voc0">waveflow-ljspeech</a>
      </td>
    </tr>
    <tr>
      <td >Parallel WaveGAN</td>
小湉湉's avatar
小湉湉 已提交
424
      <td >LJSpeech / VCTK / CSMSC / AISHELL-3</td>
M
Mingxue-Xu 已提交
425
      <td>
小湉湉's avatar
小湉湉 已提交
426
      <a href = "./examples/ljspeech/voc1">PWGAN-ljspeech</a> / <a href = "./examples/vctk/voc1">PWGAN-vctk</a> / <a href = "./examples/csmsc/voc1">PWGAN-csmsc</a> /  <a href = "./examples/aishell3/voc1">PWGAN-aishell3</a>
M
Mingxue-Xu 已提交
427 428
      </td>
    </tr>
小湉湉's avatar
小湉湉 已提交
429 430 431 432 433 434
    <tr>
      <td >Multi Band MelGAN</td>
      <td >CSMSC</td>
      <td>
      <a href = "./examples/csmsc/voc3">Multi Band MelGAN-csmsc</a> 
      </td>
小湉湉's avatar
小湉湉 已提交
435 436 437 438 439 440 441 442 443 444
    </tr> 
    <tr>
      <td >Style MelGAN</td>
      <td >CSMSC</td>
      <td>
      <a href = "./examples/csmsc/voc4">Style MelGAN-csmsc</a> 
      </td>
    </tr>
    <tr>
      <td >HiFiGAN</td>
小湉湉's avatar
小湉湉 已提交
445
      <td >LJSpeech / VCTK / CSMSC / AISHELL-3</td>
小湉湉's avatar
小湉湉 已提交
446
      <td>
小湉湉's avatar
小湉湉 已提交
447
      <a href = "./examples/ljspeech/voc5">HiFiGAN-ljspeech</a> / <a href = "./examples/vctk/voc5">HiFiGAN-vctk</a> / <a href = "./examples/csmsc/voc5">HiFiGAN-csmsc</a> / <a href = "./examples/aishell3/voc5">HiFiGAN-aishell3</a>
小湉湉's avatar
小湉湉 已提交
448
      </td>
小湉湉's avatar
小湉湉 已提交
449 450 451 452 453 454 455 456
    </tr>
    <tr>
      <td >WaveRNN</td>
      <td >CSMSC</td>
      <td>
      <a href = "./examples/csmsc/voc6">WaveRNN-csmsc</a>
      </td>
    </tr>
M
Mingxue-Xu 已提交
457
    <tr>
小湉湉's avatar
小湉湉 已提交
458 459
      <td rowspan="3">Voice Cloning</td>
      <td>GE2E</td>
小湉湉's avatar
小湉湉 已提交
460
      <td >Librispeech, etc.</td>
小湉湉's avatar
小湉湉 已提交
461 462 463
      <td>
      <a href = "./examples/other/ge2e">ge2e</a>
      </td>
M
Mingxue-Xu 已提交
464 465
    </tr>
    <tr>
小湉湉's avatar
小湉湉 已提交
466 467 468 469 470 471 472 473 474 475 476 477
      <td>GE2E + Tactron2</td>
      <td>AISHELL-3</td>
      <td>
      <a href = "./examples/aishell3/vc0">ge2e-tactron2-aishell3</a>
      </td>
    </tr>
    <tr>
      <td>GE2E + FastSpeech2</td>
      <td>AISHELL-3</td>
      <td>
      <a href = "./examples/aishell3/vc1">ge2e-fastspeech2-aishell3</a>
      </td>
M
Mingxue-Xu 已提交
478 479 480
    </tr>
  </tbody>
</table>
H
Hui Zhang 已提交
481

I
iftaken 已提交
482 483
<a name="AudioClassification"></a>

M
Mingxue-Xu 已提交
484
**Audio Classification**
485 486 487 488

<table style="width:100%">
  <thead>
    <tr>
小湉湉's avatar
小湉湉 已提交
489 490 491 492
      <th> Task </th>
      <th> Dataset </th>
      <th> Model Type </th>
      <th> Link </th>
493 494 495 496 497 498 499 500 501 502 503 504 505 506
    </tr>
  </thead>
  <tbody>
  <tr>
      <td>Audio Classification</td>
      <td>ESC-50</td>
      <td>PANN</td>
      <td>
      <a href = "./examples/esc50/cls0">pann-esc50</a>
      </td>
    </tr>
  </tbody>
</table>

I
iftaken 已提交
507 508
<a name="SpeakerVerification"></a>

509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531
**Speaker Verification**

<table style="width:100%">
  <thead>
    <tr>
      <th> Task </th>
      <th> Dataset </th>
      <th> Model Type </th>
      <th> Link </th>
    </tr>
  </thead>
  <tbody>
  <tr>
      <td>Speaker Verification</td>
      <td>VoxCeleb12</td>
      <td>ECAPA-TDNN</td>
      <td>
      <a href = "./examples/voxceleb/sv0">ecapa-tdnn-voxceleb12</a>
      </td>
    </tr>
  </tbody>
</table>

I
iftaken 已提交
532 533
<a name="PunctuationRestoration"></a>

小湉湉's avatar
小湉湉 已提交
534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556
**Punctuation Restoration**

<table style="width:100%">
  <thead>
    <tr>
      <th> Task </th>
      <th> Dataset </th>
      <th> Model Type </th>
      <th> Link </th>
    </tr>
  </thead>
  <tbody>
  <tr>
      <td>Punctuation Restoration</td>
      <td>IWLST2012_zh</td>
      <td>Ernie Linear</td>
      <td>
      <a href = "./examples/iwslt2012/punc0">iwslt2012-punc0</a>
      </td>
    </tr>
  </tbody>
</table>

M
Mingxue-Xu 已提交
557
## Documents
Z
Zeyu Chen 已提交
558

M
Mingxue-Xu 已提交
559
Normally, [Speech SoTA](https://paperswithcode.com/area/speech), [Audio SoTA](https://paperswithcode.com/area/audio) and [Music SoTA](https://paperswithcode.com/area/music) give you an overview of the hot academic topics in the related area. To focus on the tasks in PaddleSpeech, you will find the following guidelines are helpful to grasp the core ideas.
Z
Zeyu Chen 已提交
560

561
- [Installation](./docs/source/install.md)
G
grasswolfs 已提交
562 563
- [Quick Start](#quickstart)
- [Some Demos](./demos/README.md)
M
Mingxue-Xu 已提交
564 565 566 567 568 569 570 571 572 573
- Tutorials
  - [Automatic Speech Recognition](./docs/source/asr/quick_start.md)
    - [Introduction](./docs/source/asr/models_introduction.md)
    - [Data Preparation](./docs/source/asr/data_preparation.md)
    - [Ngram LM](./docs/source/asr/ngram_lm.md)
  - [Text-to-Speech](./docs/source/tts/quick_start.md)
    - [Introduction](./docs/source/tts/models_introduction.md)
    - [Advanced Usage](./docs/source/tts/advanced_usage.md)
    - [Chinese Rule Based Text Frontend](./docs/source/tts/zh_text_frontend.md)
    - [Test Audio Samples](https://paddlespeech.readthedocs.io/en/latest/tts/demo.html)
I
iftaken 已提交
574 575 576
  - Speaker Verification
    - [Audio Searching](./demos/audio_searching/README.md)
    - [Speaker Verification](./demos/speaker_verification/README.md)
G
grasswolfs 已提交
577 578
  - [Audio Classification](./demos/audio_tagging/README.md)
  - [Speech Translation](./demos/speech_translation/README.md)
I
iftaken 已提交
579
  - [Speech Server](./demos/speech_server/README.md)
M
Mingxue-Xu 已提交
580
- [Released Models](./docs/source/released_model.md)
I
iftaken 已提交
581 582 583 584 585
  - [Speech-to-Text](#SpeechToText)
  - [Text-to-Speech](#TextToSpeech)
  - [Audio Classification](#AudioClassification)
  - [Speaker Verification](#SpeakerVerification)
  - [Punctuation Restoration](#PunctuationRestoration)
G
grasswolfs 已提交
586 587
- [Community](#Community)
- [Welcome to contribute](#contribution)
G
grasswolfs 已提交
588
- [License](#License)
Z
Zeyu Chen 已提交
589

M
Mingxue-Xu 已提交
590
The Text-to-Speech module is originally called [Parakeet](https://github.com/PaddlePaddle/Parakeet), and now merged with this repository. If you are interested in academic research about this task, please see [TTS research overview](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/docs/source/tts#overview). Also, [this document](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/source/tts/models_introduction.md) is a good guideline for the pipeline components.
Z
Zeyu Chen 已提交
591

Z
Zeyu Chen 已提交
592
## Citation
593

M
Mingxue-Xu 已提交
594 595 596 597 598
To cite PaddleSpeech for research, please use the following format.
```tex
@misc{ppspeech2021,
title={PaddleSpeech, a toolkit for audio processing based on PaddlePaddle.},
author={PaddlePaddle Authors},
Z
Zeyu Chen 已提交
599
howpublished = {\url{https://github.com/PaddlePaddle/PaddleSpeech}},
M
Mingxue-Xu 已提交
600 601
year={2021}
}
H
Hui Zhang 已提交
602 603 604 605 606 607 608 609 610

@inproceedings{zheng2021fused,
  title={Fused acoustic and text encoding for multimodal bilingual pretraining and speech translation},
  author={Zheng, Renjie and Chen, Junkun and Ma, Mingbo and Huang, Liang},
  booktitle={International Conference on Machine Learning},
  pages={12736--12746},
  year={2021},
  organization={PMLR}
}
M
Mingxue-Xu 已提交
611
```
H
Hui Zhang 已提交
612

G
grasswolfs 已提交
613
<a name="contribution"></a>
M
Mingxue-Xu 已提交
614
## Contribute to PaddleSpeech
Z
Zeyu Chen 已提交
615

M
Mingxue-Xu 已提交
616
You are warmly welcome to submit questions in [discussions](https://github.com/PaddlePaddle/PaddleSpeech/discussions) and bug reports in [issues](https://github.com/PaddlePaddle/PaddleSpeech/issues)! Also, we highly appreciate if you are willing to contribute to this project!
Z
Zeyu Chen 已提交
617

M
Mingxue-Xu 已提交
618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656
### Contributors
<p align="center">
<a href="https://github.com/zh794390558"><img src="https://avatars.githubusercontent.com/u/3038472?v=4" width=75 height=75></a>
<a href="https://github.com/Jackwaterveg"><img src="https://avatars.githubusercontent.com/u/87408988?v=4" width=75 height=75></a>
<a href="https://github.com/yt605155624"><img src="https://avatars.githubusercontent.com/u/24568452?v=4" width=75 height=75></a>
<a href="https://github.com/kuke"><img src="https://avatars.githubusercontent.com/u/3064195?v=4" width=75 height=75></a>
<a href="https://github.com/xinghai-sun"><img src="https://avatars.githubusercontent.com/u/7038341?v=4" width=75 height=75></a>
<a href="https://github.com/pkuyym"><img src="https://avatars.githubusercontent.com/u/5782283?v=4" width=75 height=75></a>
<a href="https://github.com/KPatr1ck"><img src="https://avatars.githubusercontent.com/u/22954146?v=4" width=75 height=75></a>
<a href="https://github.com/LittleChenCc"><img src="https://avatars.githubusercontent.com/u/10339970?v=4" width=75 height=75></a>
<a href="https://github.com/745165806"><img src="https://avatars.githubusercontent.com/u/20623194?v=4" width=75 height=75></a>
<a href="https://github.com/Mingxue-Xu"><img src="https://avatars.githubusercontent.com/u/92848346?v=4" width=75 height=75></a>
<a href="https://github.com/chrisxu2016"><img src="https://avatars.githubusercontent.com/u/18379485?v=4" width=75 height=75></a>
<a href="https://github.com/lfchener"><img src="https://avatars.githubusercontent.com/u/6771821?v=4" width=75 height=75></a>
<a href="https://github.com/luotao1"><img src="https://avatars.githubusercontent.com/u/6836917?v=4" width=75 height=75></a>
<a href="https://github.com/wanghaoshuang"><img src="https://avatars.githubusercontent.com/u/7534971?v=4" width=75 height=75></a>
<a href="https://github.com/gongel"><img src="https://avatars.githubusercontent.com/u/24390500?v=4" width=75 height=75></a>
<a href="https://github.com/mmglove"><img src="https://avatars.githubusercontent.com/u/38800877?v=4" width=75 height=75></a>
<a href="https://github.com/iclementine"><img src="https://avatars.githubusercontent.com/u/16222986?v=4" width=75 height=75></a>
<a href="https://github.com/ZeyuChen"><img src="https://avatars.githubusercontent.com/u/1371212?v=4" width=75 height=75></a>
<a href="https://github.com/AK391"><img src="https://avatars.githubusercontent.com/u/81195143?v=4" width=75 height=75></a>
<a href="https://github.com/qingqing01"><img src="https://avatars.githubusercontent.com/u/7845005?v=4" width=75 height=75></a>
<a href="https://github.com/ericxk"><img src="https://avatars.githubusercontent.com/u/4719594?v=4" width=75 height=75></a>
<a href="https://github.com/kvinwang"><img src="https://avatars.githubusercontent.com/u/6442159?v=4" width=75 height=75></a>
<a href="https://github.com/jiqiren11"><img src="https://avatars.githubusercontent.com/u/82639260?v=4" width=75 height=75></a>
<a href="https://github.com/AshishKarel"><img src="https://avatars.githubusercontent.com/u/58069375?v=4" width=75 height=75></a>
<a href="https://github.com/chesterkuo"><img src="https://avatars.githubusercontent.com/u/6285069?v=4" width=75 height=75></a>
<a href="https://github.com/tensor-tang"><img src="https://avatars.githubusercontent.com/u/21351065?v=4" width=75 height=75></a>
<a href="https://github.com/hysunflower"><img src="https://avatars.githubusercontent.com/u/52739577?v=4" width=75 height=75></a>  
<a href="https://github.com/wwhu"><img src="https://avatars.githubusercontent.com/u/6081200?v=4" width=75 height=75></a>
<a href="https://github.com/lispc"><img src="https://avatars.githubusercontent.com/u/2833376?v=4" width=75 height=75></a>
<a href="https://github.com/jerryuhoo"><img src="https://avatars.githubusercontent.com/u/24245709?v=4" width=75 height=75></a>
<a href="https://github.com/harisankarh"><img src="https://avatars.githubusercontent.com/u/1307053?v=4" width=75 height=75></a>
<a href="https://github.com/Jackiexiao"><img src="https://avatars.githubusercontent.com/u/18050469?v=4" width=75 height=75></a>
<a href="https://github.com/limpidezza"><img src="https://avatars.githubusercontent.com/u/71760778?v=4" width=75 height=75></a>
</p>

## Acknowledgement

H
Hui Zhang 已提交
657

658
- Many thanks to [yeyupiaoling](https://github.com/yeyupiaoling)/[PPASR](https://github.com/yeyupiaoling/PPASR)/[PaddlePaddle-DeepSpeech](https://github.com/yeyupiaoling/PaddlePaddle-DeepSpeech)/[VoiceprintRecognition-PaddlePaddle](https://github.com/yeyupiaoling/VoiceprintRecognition-PaddlePaddle)/[AudioClassification-PaddlePaddle](https://github.com/yeyupiaoling/AudioClassification-PaddlePaddle) for years of attention, constructive advice and great help.
659
- Many thanks to [mymagicpower](https://github.com/mymagicpower) for the Java implementation of ASR upon [short](https://github.com/mymagicpower/AIAS/tree/main/3_audio_sdks/asr_sdk) and [long](https://github.com/mymagicpower/AIAS/tree/main/3_audio_sdks/asr_long_audio_sdk) audio files.
H
Hui Zhang 已提交
660 661
- Many thanks to [JiehangXie](https://github.com/JiehangXie)/[PaddleBoBo](https://github.com/JiehangXie/PaddleBoBo) for developing Virtual Uploader(VUP)/Virtual YouTuber(VTuber) with PaddleSpeech TTS function.
- Many thanks to [745165806](https://github.com/745165806)/[PaddleSpeechTask](https://github.com/745165806/PaddleSpeechTask) for contributing Punctuation Restoration model.
L
lizi 已提交
662
- Many thanks to [kslz](https://github.com/745165806) for supplementary Chinese documents.
P
Phecda xu 已提交
663
- Many thanks to [awmmmm](https://github.com/awmmmm) for contributing fastspeech2 aishell3 conformer pretrained model.
P
Phecda xu 已提交
664
- Many thanks to [phecda-xu](https://github.com/phecda-xu)/[PaddleDubbing](https://github.com/phecda-xu/PaddleDubbing) for developing a dubbing tool with GUI based on PaddleSpeech TTS model.
J
Jerryuhoo 已提交
665
- Many thanks to [jerryuhoo](https://github.com/jerryuhoo)/[VTuberTalk](https://github.com/jerryuhoo/VTuberTalk) for developing a GUI tool based on PaddleSpeech TTS and code for making datasets from videos based on PaddleSpeech ASR.
M
Mingxue-Xu 已提交
666 667 668

Besides, PaddleSpeech depends on a lot of open source repositories. See [references](./docs/source/reference.md) for more information.

G
grasswolfs 已提交
669
<a name="License"></a>
M
Mingxue-Xu 已提交
670 671 672
## License

PaddleSpeech is provided under the [Apache-2.0 License](./LICENSE).