README.md 26.2 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>
M
Mingxue-Xu 已提交
10
  | <a href="#documents"> Documents </a>
Z
Zeyu Chen 已提交
11
  | <a href="#model-list"> Models List </a>
M
Mingxue-Xu 已提交
12 13 14
</div>

------------------------------------------------------------------------------------
Z
Zeyu Chen 已提交
15

G
grasswolfs 已提交
16 17

<p align="center">
小湉湉's avatar
小湉湉 已提交
18
    <a href="./LICENSE"><img src="https://img.shields.io/badge/license-Apache%202-red.svg"></a>
H
Hui Zhang 已提交
19 20
    <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
21 22 23
    <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
24 25
    <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
26 27
    <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
28
    <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
29
</p>
L
lfchener 已提交
30

M
Mingxue-Xu 已提交
31

32
**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
33

H
Hui Zhang 已提交
34
##### Speech Recognition
M
Mingxue-Xu 已提交
35 36 37 38 39 40

<div align = "center">
<table style="width:100%">
  <thead>
    <tr>
      <th> Input Audio  </th>
M
Mingxue-Xu 已提交
41
      <th width="550"> Recognition Result  </th>
M
Mingxue-Xu 已提交
42 43 44 45 46
    </tr>
  </thead>
  <tbody>
   <tr>
      <td align = "center">
M
Mingxue-Xu 已提交
47
      <a href="https://paddlespeech.bj.bcebos.com/PaddleAudio/en.wav" rel="nofollow">
M
Mingxue-Xu 已提交
48
            <img align="center" src="./docs/images/audio_icon.png" width="200 style="max-width: 100%;"></a><br>
M
Mingxue-Xu 已提交
49
      </td>
M
Mingxue-Xu 已提交
50
      <td >I knocked at the door on the ancient side of the building.</td>
M
Mingxue-Xu 已提交
51 52 53
    </tr>
    <tr>
      <td align = "center">
M
Mingxue-Xu 已提交
54
      <a href="https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav" rel="nofollow">
M
Mingxue-Xu 已提交
55
            <img align="center" src="./docs/images/audio_icon.png" width="200" style="max-width: 100%;"></a><br>
M
Mingxue-Xu 已提交
56
      </td>
M
Mingxue-Xu 已提交
57
      <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
58
    </tr>
M
Mingxue-Xu 已提交
59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81
  </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
82 83 84 85
  </tbody>
</table>

</div>
86

Z
Zeyu Chen 已提交
87
##### Text-to-Speech
M
Mingxue-Xu 已提交
88 89 90 91
<div align = "center">
<table style="width:100%">
  <thead>
    <tr>
小湉湉's avatar
小湉湉 已提交
92
      <th width="550" > Input Text</th>
M
Mingxue-Xu 已提交
93 94 95 96 97 98 99
      <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
100
      <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
101 102 103 104 105 106 107 108 109 110
            <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
111 112 113 114 115 116 117
    <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
118 119 120 121 122
  </tbody>
</table>

</div>

Z
Zeyu Chen 已提交
123
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
124

小湉湉's avatar
小湉湉 已提交
125
##### Punctuation Restoration
K
KP 已提交
126 127 128 129
<div align = "center">
<table style="width:100%">
  <thead>
    <tr>
小湉湉's avatar
小湉湉 已提交
130 131
      <th width="390"> Input Text </th>
      <th width="390"> Output Text </th>
K
KP 已提交
132 133 134 135 136 137 138 139 140 141 142 143
    </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>

144 145 146 147 148
### ⭐ 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
149
- [PaddleSpeech Demo Video](https://paddlespeech.readthedocs.io/en/latest/demo_video.html)
150

J
Jerryuhoo 已提交
151
- **[VTuberTalk](https://github.com/jerryuhoo/VTuberTalk): Use PaddleSpeech TTS and ASR to clone voice from videos.**
J
Jerryuhoo 已提交
152 153 154 155 156

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

157 158 159 160 161 162 163 164 165
### 🔥 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
166

M
Mingxue-Xu 已提交
167
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
168 169 170
- 📦  **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
171
- **Varieties of Functions that Vitalize both Industrial and Academia**:
小湉湉's avatar
小湉湉 已提交
172 173 174
  - 🛎️  *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
175

176
### Recent Update
M
Mingxue-Xu 已提交
177 178 179 180

<!---
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
181
- 🤗  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
182
- 👏🏻  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
183

G
grasswolfs 已提交
184
### Community
小湉湉's avatar
小湉湉 已提交
185
- 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
186 187

<div align="center">
小湉湉's avatar
小湉湉 已提交
188
<img src="https://raw.githubusercontent.com/yt605155624/lanceTest/main/images/wechat_4.jpg"  width = "300"  />
M
Mingxue-Xu 已提交
189 190
</div>

Z
Zeyu Chen 已提交
191
## Installation
M
Mingxue-Xu 已提交
192

J
Jackwaterveg 已提交
193 194
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
195

G
grasswolfs 已提交
196
<a name="quickstart"></a>
Z
Zeyu Chen 已提交
197
## Quick Start
M
Mingxue-Xu 已提交
198

M
Mingxue-Xu 已提交
199
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
200

M
Mingxue-Xu 已提交
201
**Audio Classification**     
M
Mingxue-Xu 已提交
202
```shell
小湉湉's avatar
小湉湉 已提交
203
paddlespeech cls --input input.wav
M
Mingxue-Xu 已提交
204
```
H
Hui Zhang 已提交
205

M
Mingxue-Xu 已提交
206 207
**Automatic Speech Recognition**
```shell
小湉湉's avatar
小湉湉 已提交
208
paddlespeech asr --lang zh --input input_16k.wav
M
Mingxue-Xu 已提交
209
```
H
Hui Zhang 已提交
210
- 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
211

H
Hui Zhang 已提交
212
**Speech Translation** (English to Chinese)
H
huangyuxin 已提交
213
(not support for Mac and Windows now)
M
Mingxue-Xu 已提交
214
```shell
小湉湉's avatar
小湉湉 已提交
215
paddlespeech st --input input_16k.wav
M
Mingxue-Xu 已提交
216
```
H
Hui Zhang 已提交
217

M
Mingxue-Xu 已提交
218
**Text-to-Speech** 
M
Mingxue-Xu 已提交
219
```shell
G
grasswolfs 已提交
220
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
221
```
H
Hui Zhang 已提交
222
- 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
223 224 225 226 227 228 229

**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
230 231 232 233 234
**Batch Process**
```
echo -e "1 欢迎光临。\n2 谢谢惠顾。" | paddlespeech tts
```  

H
Hui Zhang 已提交
235 236
**Shell Pipeline**   
- ASR + Punctuation Restoration
H
Hui Zhang 已提交
237 238 239
```
paddlespeech asr --input ./zh.wav | paddlespeech text --task punc
```
小湉湉's avatar
小湉湉 已提交
240 241 242

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

243
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
244

Z
Zeyu Chen 已提交
245
## Model List
246

247
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
248

小湉湉's avatar
小湉湉 已提交
249
**Speech-to-Text** contains *Acoustic Model*, *Language Model*, and *Speech Translation*, with the following details:
L
lfchener 已提交
250

M
Mingxue-Xu 已提交
251 252 253
<table style="width:100%">
  <thead>
    <tr>
Z
Zeyu Chen 已提交
254
      <th>Speech-to-Text Module Type</th>
M
Mingxue-Xu 已提交
255 256 257 258 259 260 261
      <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
262
      <td rowspan="4">Speech Recogination</td>
M
Mingxue-Xu 已提交
263 264 265
      <td rowspan="2" >Aishell</td>
      <td >DeepSpeech2 RNN + Conv based Models</td>
      <td>
H
Hui Zhang 已提交
266
      <a href = "./examples/aishell/asr0">deepspeech2-aishell</a>
M
Mingxue-Xu 已提交
267 268 269 270 271
      </td>
    </tr>
    <tr>
      <td>Transformer based Attention Models </td>
      <td>
H
Hui Zhang 已提交
272
      <a href = "./examples/aishell/asr1">u2.transformer.conformer-aishell</a>
M
Mingxue-Xu 已提交
273 274
      </td>
    </tr>
小湉湉's avatar
小湉湉 已提交
275
    <tr>
M
Mingxue-Xu 已提交
276 277 278
      <td> Librispeech</td>
      <td>Transformer based Attention Models </td>
      <td>
H
Hui Zhang 已提交
279
      <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
280 281 282
      </td>
      </td>
    </tr>
小湉湉's avatar
小湉湉 已提交
283 284 285 286 287 288 289
  <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
290 291 292 293 294
  <tr>
  <td>Alignment</td>
  <td>THCHS30</td>
  <td>MFA</td>
  <td>
H
Hui Zhang 已提交
295
  <a href = ".examples/thchs30/align0">mfa-thchs30</a>
M
Mingxue-Xu 已提交
296 297
  </td>
  </tr>
M
Mingxue-Xu 已提交
298
   <tr>
小湉湉's avatar
小湉湉 已提交
299
      <td rowspan="1">Language Model</td>
M
Mingxue-Xu 已提交
300
      <td colspan = "2">Ngram Language Model</td>
M
Mingxue-Xu 已提交
301
      <td>
M
Mingxue-Xu 已提交
302
      <a href = "./examples/other/ngram_lm">kenlm</a>
M
Mingxue-Xu 已提交
303 304
      </td>
    </tr>
小湉湉's avatar
小湉湉 已提交
305
  <tr>
M
Mingxue-Xu 已提交
306 307 308 309 310 311 312 313 314 315 316 317 318
      <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
319 320
  </tbody>
</table>
H
Hui Zhang 已提交
321

322
**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
323

M
Mingxue-Xu 已提交
324 325 326
<table>
  <thead>
    <tr>
小湉湉's avatar
小湉湉 已提交
327 328 329 330
      <th> Text-to-Speech Module Type </th>
      <th> Model Type </th>
      <th> Dataset </th>
      <th> Link </th>
M
Mingxue-Xu 已提交
331 332 333 334
    </tr>
  </thead>
  <tbody>
    <tr>
小湉湉's avatar
小湉湉 已提交
335
    <td> Text Frontend </td>
M
Mingxue-Xu 已提交
336 337
    <td colspan="2"> &emsp; </td>
    <td>
338
    <a href = "./examples/other/tn">tn</a> / <a href = "./examples/other/g2p">g2p</a>
M
Mingxue-Xu 已提交
339 340 341 342
    </td>
    </tr>
    <tr>
      <td rowspan="4">Acoustic Model</td>
小湉湉's avatar
小湉湉 已提交
343 344
      <td>Tacotron2</td>
      <td>LJSpeech / CSMSC</td>
M
Mingxue-Xu 已提交
345
      <td>
小湉湉's avatar
小湉湉 已提交
346
      <a href = "./examples/ljspeech/tts0">tacotron2-ljspeech</a> / <a href = "./examples/csmsc/tts0">tacotron2-csmsc</a>
M
Mingxue-Xu 已提交
347 348 349
      </td>
    </tr>
    <tr>
小湉湉's avatar
小湉湉 已提交
350
      <td>Transformer TTS</td>
小湉湉's avatar
小湉湉 已提交
351
      <td>LJSpeech</td>
M
Mingxue-Xu 已提交
352 353 354 355 356 357 358 359 360 361 362 363 364
      <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
365
      <td>LJSpeech / VCTK / CSMSC / AISHELL-3</td>
M
Mingxue-Xu 已提交
366
      <td>
小湉湉's avatar
小湉湉 已提交
367
      <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
368 369 370
      </td>
    </tr>
   <tr>
小湉湉's avatar
小湉湉 已提交
371
      <td rowspan="6">Vocoder</td>
M
Mingxue-Xu 已提交
372 373 374 375 376 377 378 379
      <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
380
      <td >LJSpeech / VCTK / CSMSC / AISHELL-3</td>
M
Mingxue-Xu 已提交
381
      <td>
小湉湉's avatar
小湉湉 已提交
382
      <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
383 384
      </td>
    </tr>
小湉湉's avatar
小湉湉 已提交
385 386 387 388 389 390
    <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
391 392 393 394 395 396 397 398 399 400
    </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
401
      <td >LJSpeech / VCTK / CSMSC / AISHELL-3</td>
小湉湉's avatar
小湉湉 已提交
402
      <td>
小湉湉's avatar
小湉湉 已提交
403
      <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
404
      </td>
小湉湉's avatar
小湉湉 已提交
405 406 407 408 409 410 411 412
    </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
413
    <tr>
小湉湉's avatar
小湉湉 已提交
414 415
      <td rowspan="3">Voice Cloning</td>
      <td>GE2E</td>
小湉湉's avatar
小湉湉 已提交
416
      <td >Librispeech, etc.</td>
小湉湉's avatar
小湉湉 已提交
417 418 419
      <td>
      <a href = "./examples/other/ge2e">ge2e</a>
      </td>
M
Mingxue-Xu 已提交
420 421
    </tr>
    <tr>
小湉湉's avatar
小湉湉 已提交
422 423 424 425 426 427 428 429 430 431 432 433
      <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
434 435 436
    </tr>
  </tbody>
</table>
H
Hui Zhang 已提交
437

M
Mingxue-Xu 已提交
438
**Audio Classification**
439 440 441 442

<table style="width:100%">
  <thead>
    <tr>
小湉湉's avatar
小湉湉 已提交
443 444 445 446
      <th> Task </th>
      <th> Dataset </th>
      <th> Model Type </th>
      <th> Link </th>
447 448 449 450 451 452 453 454 455 456 457 458 459 460
    </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>

小湉湉's avatar
小湉湉 已提交
461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483
**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
484
## Documents
Z
Zeyu Chen 已提交
485

M
Mingxue-Xu 已提交
486
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
487

488
- [Installation](./docs/source/install.md)
G
grasswolfs 已提交
489 490
- [Quick Start](#quickstart)
- [Some Demos](./demos/README.md)
M
Mingxue-Xu 已提交
491 492 493 494 495 496 497 498 499 500
- 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)
G
grasswolfs 已提交
501 502
  - [Audio Classification](./demos/audio_tagging/README.md)
  - [Speech Translation](./demos/speech_translation/README.md)
M
Mingxue-Xu 已提交
503
- [Released Models](./docs/source/released_model.md)
G
grasswolfs 已提交
504 505
- [Community](#Community)
- [Welcome to contribute](#contribution)
G
grasswolfs 已提交
506
- [License](#License)
Z
Zeyu Chen 已提交
507

M
Mingxue-Xu 已提交
508
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
509

Z
Zeyu Chen 已提交
510
## Citation
511

M
Mingxue-Xu 已提交
512 513 514 515 516
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
517
howpublished = {\url{https://github.com/PaddlePaddle/PaddleSpeech}},
M
Mingxue-Xu 已提交
518 519
year={2021}
}
H
Hui Zhang 已提交
520 521 522 523 524 525 526 527 528

@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
529
```
H
Hui Zhang 已提交
530

G
grasswolfs 已提交
531
<a name="contribution"></a>
M
Mingxue-Xu 已提交
532
## Contribute to PaddleSpeech
Z
Zeyu Chen 已提交
533

M
Mingxue-Xu 已提交
534
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
535

M
Mingxue-Xu 已提交
536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574
### 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
575

576
- 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.
577
- 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
578 579
- 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
580
- Many thanks to [kslz](https://github.com/745165806) for supplementary Chinese documents.
P
Phecda xu 已提交
581
- Many thanks to [awmmmm](https://github.com/awmmmm) for contributing fastspeech2 aishell3 conformer pretrained model.
P
Phecda xu 已提交
582
- 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
583
- 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
584 585 586

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

G
grasswolfs 已提交
587
<a name="License"></a>
M
Mingxue-Xu 已提交
588 589 590
## License

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