**PaddleSpeech** is an open-source toolkit on [PaddlePaddle](https://github.com/PaddlePaddle/Paddle) platform for a variety of critical tasks in speech, with state-of-art and influential models.
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:
- **Fast and Light-weight**: we provide high-speed and ultra-lightweight models that are convenient for industrial deployment.
- **Rule-based Chinese frontend**: our frontend contains Text Normalization (TN) and Grapheme-to-Phoneme (G2P, including Polyphone and Tone Sandhi). Moreover, we use self-defined linguistic rules to adapt Chinese context.
- **Varieties of Functions that Vitalize both Industrial and Academia**:
- *Implementation of critical audio tasks*: this toolkit contains audio functions like Speech Translation (ST), Automatic Speech Recognition (ASR), Text-To-Speech Synthesis (TTS), Voice Cloning(VC), Punctuation Restoration, 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 lists](#models-list) for more details.
- *Cross-domain application*: as an extension of the application of traditional audio tasks, we combine the aforementioned tasks with other fields like NLP.
If you want to set up PaddleSpeech in other environment, please see the [ASR installation](docs/source/asr/install.md) and [TTS installation](docs/source/tts/install.md) documents for all the alternatives.
Just a quick test of our functions: [English ASR](link/hubdetail?name=deepspeech2_aishell&en_category=AutomaticSpeechRecognition) and [English TTS](link/hubdetail?name=fastspeech2_baker&en_category=TextToSpeech) by typing message or upload your own audio file.
- Download LJSpeech-1.1 from the [ljspeech official website](https://keithito.com/LJ-Speech-Dataset/), our prepared durations for fastspeech2 [ljspeech_alignment](https://paddlespeech.bj.bcebos.com/MFA/LJSpeech-1.1/ljspeech_alignment.tar.gz).
- The pretrained models are seperated into two parts: [fastspeech2_nosil_ljspeech_ckpt](https://paddlespeech.bj.bcebos.com/Parakeet/fastspeech2_nosil_ljspeech_ckpt_0.5.zip) and [pwg_ljspeech_ckpt](https://paddlespeech.bj.bcebos.com/Parakeet/pwg_ljspeech_ckpt_0.5.zip). Please download then unzip to `./model/fastspeech2` and `./model/pwg` respectively.
- Assume your path to the dataset is `~/datasets/LJSpeech-1.1` and `./ljspeech_alignment` accordingly, preprocess your data and then use our pretrained model to synthesize:
If you want to try more functions like training and tuning, please see [ASR getting started](docs/source/asr/getting_started.md) and [TTS Basic Use](/docs/source/tts/basic_usage.md).
PaddleSpeech supports a series of most popular models, summarized in [released models](./docs/source/released_model.md) with available pretrained models.
<ahref ="https://deepspeech.bj.bcebos.com/en_lm/common_crawl_00.prune01111.trie.klm">English Language Model</a>
</td>
</tr>
<tr>
<tdrowspan="2">Baidu Internal Corpus</td>
<td>Mandarin Language Model Small</td>
<td>
<ahref ="https://deepspeech.bj.bcebos.com/zh_lm/zh_giga.no_cna_cmn.prune01244.klm">Mandarin Language Model Small</a>
</td>
</tr>
<tr>
<td>Mandarin Language Model Large</td>
<td>
<ahref ="https://deepspeech.bj.bcebos.com/zh_lm/zhidao_giga.klm">Mandarin Language Model Large</a>
</td>
</tr>
</tbody>
</table>
PaddleSpeech TTS mainly contains three modules: *Text Frontend*, *Acoustic Model* and *Vocoder*. Acoustic Model and Vocoder models are listed as follow:
Normally, [Speech SoTA](https://paperswithcode.com/area/speech) gives you an overview of the hot academic topics in speech. If you want to focus on the two tasks in PaddleSpeech, you will find the following guidelines are helpful to grasp the core ideas.
The original ASR module is based on [Baidu's DeepSpeech](https://arxiv.org/abs/1412.5567) which is an independent product named [DeepSpeech](https://deepspeech.readthedocs.io). However, the toolkit aligns almost all the SoTA modules in the pipeline. Specifically, these modules are
The TTS module is originally called [Parakeet](https://github.com/PaddlePaddle/Parakeet), and now merged with DeepSpeech. If you are interested in academic research about this function, please see [TTS research overview](https://github.com/PaddlePaddle/DeepSpeech/tree/develop/docs/source/tts#overview). Also, [this document](https://paddleparakeet.readthedocs.io/en/latest/released_models.html) is a good guideline for the pipeline components.
You are warmly welcome to submit questions in [discussions](https://github.com/PaddlePaddle/DeepSpeech/discussions) and bug reports in [issues](https://github.com/PaddlePaddle/DeepSpeech/issues)! Also, we highly appreciate if you would like to contribute to this project!
