OrgLion-ML
/
ASRT_SpeechRecognition
mirror of https://github.com/nl8590687/ASRT_SpeechRecognition.git
1
0
Fork 0
Code Issues Releases Wiki Activity

docs: update readme

This commit is contained in:
ailemon 2022-04-06 13:01:39 +08:00
parent 5eb15b0c3a
commit edbf9acc2c
2 changed files with 8 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
README.md
View File

@ -11,7 +11,7 @@ ASRT是一个基于深度学习的中文语音识别系统，如果您觉得喜
**ReadMe Language** | 中文版 | [English](https://github.com/nl8590687/ASRT_SpeechRecognition/blob/master/README_EN.md) | **ReadMe Language** | 中文版 | [English](https://github.com/nl8590687/ASRT_SpeechRecognition/blob/master/README_EN.md) |
[**ASRT项目主页**](https://asrt.ailemon.net/) | [**ASRT项目主页**](https://asrt.ailemon.net/) |
[**发布版下载**](https://asrt.ailemon.net/download) | [**发布版下载**](https://wiki.ailemon.net/docs/asrt-doc/download) |
[**查看本项目的Wiki文档**](https://wiki.ailemon.net/docs/asrt-doc) | [**查看本项目的Wiki文档**](https://wiki.ailemon.net/docs/asrt-doc) |
[**实用效果体验Demo**](https://asrt.ailemon.net/demo) | [**实用效果体验Demo**](https://asrt.ailemon.net/demo) |
[**打赏作者**](https://wiki.ailemon.net/docs/asrt-doc/asrt-doc-1deo9u61unti9) [**打赏作者**](https://wiki.ailemon.net/docs/asrt-doc/asrt-doc-1deo9u61unti9)
@ -28,8 +28,6 @@ ASRT是一个基于深度学习的中文语音识别系统，如果您觉得喜
本项目使用tensorFlow.keras基于深度卷积神经网络和长短时记忆神经网络、注意力机制以及CTC实现。 本项目使用tensorFlow.keras基于深度卷积神经网络和长短时记忆神经网络、注意力机制以及CTC实现。
This project uses tensorFlow.keras based on deep convolutional neural network and long-short memory neural network, attention mechanism and CTC to implement.
## 训练模型的最低软硬件要求 ## 训练模型的最低软硬件要求
### 硬件 ### 硬件
* CPU: 4核 (x86_64, amd64) + * CPU: 4核 (x86_64, amd64) +
@ -105,8 +103,8 @@ $ python3 client_http.py
使用docker直接部署ASRT： 使用docker直接部署ASRT：
```shell ```shell
$ docker pull ailemondocker/asrt_service:1.1.2 $ docker pull ailemondocker/asrt_service:1.2.0
$ docker run --rm -it -p 20001:20001 --name asrt-server -d ailemondocker/asrt_service:1.1.2 $ docker run --rm -it -p 20001:20001 --name asrt-server -d ailemondocker/asrt_service:1.2.0
``` ```
仅CPU运行推理识别，不作训练 仅CPU运行推理识别，不作训练
@ -132,7 +130,7 @@ Github本仓库下[Releases](https://github.com/nl8590687/ASRT_SpeechRecognition
## About Accuracy 关于准确率 ## About Accuracy 关于准确率
当前，最好的模型在测试集上基本能达到80%的汉语拼音正确率 当前，最好的模型在测试集上基本能达到85%的汉语拼音正确率
## Python依赖库 ## Python依赖库

8
README_EN.md
View File

@ -11,7 +11,7 @@ ASRT is A Deep-Learning-Based Chinese Speech Recognition System. If you like thi
**ReadMe Language** | [中文版](https://github.com/nl8590687/ASRT_SpeechRecognition/blob/master/README.md) | English | **ReadMe Language** | [中文版](https://github.com/nl8590687/ASRT_SpeechRecognition/blob/master/README.md) | English |
[**ASRT Project Home Page**](https://asrt.ailemon.net/) | [**ASRT Project Home Page**](https://asrt.ailemon.net/) |
[**Released Download**](https://asrt.ailemon.net/download) | [**Released Download**](https://wiki.ailemon.net/docs/asrt-doc/download) |
[**View this project's wiki document (Chinese)**](https://wiki.ailemon.net/docs/asrt-doc) | [**View this project's wiki document (Chinese)**](https://wiki.ailemon.net/docs/asrt-doc) |
[**Experience Demo**](https://asrt.ailemon.net/demo) | [**Experience Demo**](https://asrt.ailemon.net/demo) |
[**Donate**](https://wiki.ailemon.net/docs/asrt-doc/asrt-doc-1deo9u61unti9) [**Donate**](https://wiki.ailemon.net/docs/asrt-doc/asrt-doc-1deo9u61unti9)
@ -103,8 +103,8 @@ If there is any problem during the execution of the program or during use, it ca
Deploy ASRT by docker： Deploy ASRT by docker：
```shell ```shell
$ docker pull ailemondocker/asrt_service:1.1.2 $ docker pull ailemondocker/asrt_service:1.2.0
$ docker run --rm -it -p 20001:20001 --name asrt-server -d ailemondocker/asrt_service:1.1.2 $ docker run --rm -it -p 20001:20001 --name asrt-server -d ailemondocker/asrt_service:1.2.0
``` ```
It will start a api server for recognition rather than training. It will start a api server for recognition rather than training.
@ -130,7 +130,7 @@ The input is a Chinese pinyin sequence, and the output is the corresponding Chin
## About Accuracy ## About Accuracy
At present, the best model can basically reach 80% of Pinyin correct rate on the test set. At present, the best model can basically reach 85% of Pinyin correct rate on the test set.
## Python Dependency Library ## Python Dependency Library