fix img link; rsl format;

pull/917/head
Hui Zhang 3 years ago
parent 3eef444dec
commit f55267f2b3

@ -14,10 +14,11 @@ In addition, the training process and the testing process are also introduced.
The arcitecture of the model is shown in Fig.1.
<p align="center">
<img src="../images/ds2onlineModel.png" width=800>
<img src="../../images/ds2onlineModel.png" width=800>
<br/>Fig.1 The Arcitecture of deepspeech2 online model
</p>
### Data Preparation
#### Vocabulary
For English data, the vocabulary dictionary is composed of 26 English characters with " ' ", space, \<blank\> and \<eos\>. The \<blank\> represents the blank label in CTC, the \<unk\> represents the unknown character and the \<eos\> represents the start and the end characters. For mandarin, the vocabulary dictionary is composed of chinese characters statisticed from the training set and three additional characters are added. The added characters are \<blank\>, \<unk\> and \<eos\>. For both English and mandarin data, we set the default indexs that \<blank\>=0, \<unk\>=1 and \<eos\>= last index.
@ -161,12 +162,13 @@ The deepspeech2 offline model is similarity to the deepspeech2 online model. The
The arcitecture of the model is shown in Fig.2.
<p align="center">
<img src="../images/ds2offlineModel.png" width=800>
<img src="../../images/ds2offlineModel.png" width=800>
<br/>Fig.2 The Arcitecture of deepspeech2 offline model
</p>
For data preparation and decoder, the deepspeech2 offline model is same with the deepspeech2 online model.
The code of encoder and decoder for deepspeech2 offline model is in:

@ -2,10 +2,11 @@
Parakeet aims to provide a flexible, efficient and state-of-the-art text-to-speech toolkit for the open-source community. It is built on PaddlePaddle dynamic graph and includes many influential TTS models.
<div align="center">
<img src="docs/images/logo.png" width=300 /> <br>
<img src="../../images/logo.png" width=300 /> <br>
</div>
## News <img src="./docs/images/news_icon.png" width="40"/>
## News <img src="../../images/news_icon.png" width="40"/>
- Oct-12-2021, Refector examples code.
- Oct-12-2021, Parallel WaveGAN with LJSpeech. Check [examples/GANVocoder/parallelwave_gan/ljspeech](./examples/GANVocoder/parallelwave_gan/ljspeech).
- Oct-12-2021, FastSpeech2/FastPitch with LJSpeech. Check [examples/fastspeech2/ljspeech](./examples/fastspeech2/ljspeech).

@ -6,6 +6,7 @@
## Data
| Data Subset | Duration in Seconds |
| ------------------- | --------------------- |
| data/manifest.train | 1.23 ~ 14.53125 |
| data/manifest.dev | 1.645 ~ 12.533 |
| data/manifest.test | 1.859125 ~ 14.6999375 |

@ -2,8 +2,7 @@
* s0 is for deepspeech2 offline
* s1 is for transformer/conformer/U2
* s2 is for transformer/conformer/U2 w/ kaldi feat
need install Kaldi
* s2 is for transformer/conformer/U2 w/ kaldi feat, need install Kaldi
## Data
| Data Subset | Duration in Seconds |

@ -1,14 +1,6 @@
# LibriSpeech
## Data
| Data Subset | Duration in Seconds |
| --- | --- |
| data/manifest.train | 0.83s ~ 29.735s |
| data/manifest.dev | 1.065 ~ 35.155s |
| data/manifest.test-clean | 1.285s ~ 34.955s |
## Deepspeech2
| Model | Params | release | Config | Test set | Loss | WER |
| --- | --- | --- | --- | --- | --- | --- |
| DeepSpeech2 | 42.96M | 2.2.0 | conf/deepspeech2.yaml + spec_aug | test-clean | 14.49190807 | 0.067283 |

@ -1,3 +1,4 @@
# Punctation Restoration
Please using [PaddleSpeechTask](https://github.com/745165806/PaddleSpeechTask] to do this task.
Please using [PaddleSpeechTask](https://github.com/745165806/PaddleSpeechTask) to do this task.

Loading…
Cancel
Save