Skip to content

Commit

Permalink
[other] 整理代码结构,剔除不要文件
Browse files Browse the repository at this point in the history
  • Loading branch information
lihanghang committed Dec 25, 2019
1 parent 69e2999 commit afde08f
Show file tree
Hide file tree
Showing 428 changed files with 46 additions and 790,593 deletions.
32 changes: 22 additions & 10 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,12 +1,24 @@
# CASR-DEMO(中文自动语音识别演示系统)
## 关于本项目的一些说明
> 首先,欢迎大家关注项目,进行学习研究。收到一些小伙伴的问题我就集中回答下,这里是demo的源码、有两个版本其一是名为speech_env,这是一个简单的语音识别功能,界面如下面的效果图一;还有一个是V2.0的目录,这个版本功能比较齐全,界面如效果图二。大家感兴趣在自己机器上试试的话我推荐直接使用v2.0版本,还有一点项目只在win10平台上测试过,其他不保证能不能运行。由于月久失更,有些依赖包可能需要修改,不过应该都是小问题,根据实际过程的报错信息修复就行。再次感谢大家的关注!
## speech_env(效果图一)
![效果图1](./image/CASR_DEMO_up.png)
## speechV2.0 基于第三方接口实现语音识别和语音合成、说话人识别功能(效果图二)
![效果图2](./image/asr_tts.png)
# CASR-DEMO(中文自动语音识别演示系统)V1.0版本
## Introdction
- ~~ Note: 本系统仅是尝试使用已训练完成的语音模型,不涉及模型训练部分。对模型训练感兴趣的小伙伴,详细可参考:来自-AI柠檬 的[ASRT_SpeechRecognition](https://github.com/nl8590687/ASRT_SpeechRecognition)(A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统)。(本版本不支持该方法)~~
- 本系统使用Flask框架建立Web系统,主要由语音录制和语音识别两部分组成,其中:
+ 效果图
![效果图1](./image/CASR_DEMO_up.png)
1. 语音录制。基于PyAudio是Python下的一个音频处理模块,用于将音频流输送到计算机声卡上。保存录音到本地。
2. 语音识别。集成已训练模型实现,读取保存的录音并输出。
- <strong>目前为更好体验语音识别技术,系统已支持调用百度语音识别[API](https://ai.baidu.com/docs#/ASR-Online-Python-SDK/top)实现。录音时长不超过60秒!</strong>

## Usage
~~ - 根据实际情况,在CASR_model.py中修改相关文件路径。~~
~~ - 进入speech_env目录下,使用source venv/bin/activate命令进入虚拟环境 ~~
- 直接使用命令:python manage.py 启动Falsk服务器,根据提示地址在浏览器访问即可。(这里肯定会出现某些包不存在的情况,不用慌,我们坚持”少什么,装什么“的原则,耐心装上即可,大概需要装4-6个左右的包。)


## Ohters
- 因仅为体验所用,所以在用户体验上没有耗费过多时间。小伙伴可根据个人喜好发挥想象任意DIY.
- 如:实现人为控制停止录音。
---
wechat:LHH754086474
[CSDN](https://blog.csdn.net/lihangll)
Updated on December 24,2019.
E-mail: [email protected]
[更多了解](https://lihanghang.top)
Updated on December 25,2019.

Binary file removed image/asr_tts.png
Binary file not shown.
24 changes: 24 additions & 0 deletions speech2text_V1.0/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
# CASR-DEMO(中文自动语音识别演示系统)V1.0版本
## Introdction
- ~~ Note: 本系统仅是尝试使用已训练完成的语音模型,不涉及模型训练部分。对模型训练感兴趣的小伙伴,详细可参考:来自-AI柠檬 的[ASRT_SpeechRecognition](https://github.com/nl8590687/ASRT_SpeechRecognition)(A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统)。(本版本不支持该方法)~~
- 本系统使用Flask框架建立Web系统,主要由语音录制和语音识别两部分组成,其中:
+ 效果图
![效果图1](./image/CASR_DEMO_up.png)
1. 语音录制。基于PyAudio是Python下的一个音频处理模块,用于将音频流输送到计算机声卡上。保存录音到本地。
2. 语音识别。集成已训练模型实现,读取保存的录音并输出。
- <strong>目前为更好体验语音识别技术,系统已支持调用百度语音识别[API](https://ai.baidu.com/docs#/ASR-Online-Python-SDK/top)实现。录音时长不超过60秒!</strong>

## Usage
~~ - 根据实际情况,在CASR_model.py中修改相关文件路径。~~
~~ - 进入speech_env目录下,使用source venv/bin/activate命令进入虚拟环境 ~~
- 直接使用命令:python manage.py 启动Falsk服务器,根据提示地址在浏览器访问即可。(这里肯定会出现某些包不存在的情况,不用慌,我们坚持”少什么,装什么“的原则,耐心装上即可,大概需要装4-6个左右的包。)


## Ohters
- 因仅为体验所用,所以在用户体验上没有耗费过多时间。小伙伴可根据个人喜好发挥想象任意DIY.
- 如:实现人为控制停止录音。
---
E-mail: [email protected]
[更多了解](https://lihanghang.top)
Updated on December 25,2019.

File renamed without changes.
File renamed without changes.
File renamed without changes.
Original file line number Diff line number Diff line change
@@ -1,7 +1,6 @@
# -*-coding:utf-8 -*-
import wave
from pyaudio import PyAudio, paInt16
from main import CASR_model
import json
from datetime import datetime
from main import baidu_aip
Expand Down
File renamed without changes.
1 change: 0 additions & 1 deletion speech_env/manage.py → speech2text_V1.0/manage.py
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,6 @@ def stopRecorder():
# 开始识别
@app.route("/recognize", methods=['GET', 'POST'])
def recognize():
#return CASR_model.modelAPI() # 自训模型
return baidu_aip.baiduAPI() # baidu语音识别接口


Expand Down
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
48 changes: 0 additions & 48 deletions speechV2.0/SR/gmm_train.py

This file was deleted.

39 changes: 0 additions & 39 deletions speechV2.0/SR/mfcc_coeff.py

This file was deleted.

38 changes: 0 additions & 38 deletions speechV2.0/SR/record_voice.py

This file was deleted.

109 changes: 0 additions & 109 deletions speechV2.0/SR/register.py

This file was deleted.

Binary file removed speechV2.0/SR/samples/hang-2018/hang_down.wav
Binary file not shown.
Binary file removed speechV2.0/SR/samples/hang-2018/hang_left.wav
Binary file not shown.
Binary file removed speechV2.0/SR/samples/hang-2018/hang_up.wav
Binary file not shown.
Binary file removed speechV2.0/SR/samples/jingkun-2018/jingkun_down.wav
Binary file not shown.
Binary file removed speechV2.0/SR/samples/jingkun-2018/jingkun_left.wav
Binary file not shown.
Binary file removed speechV2.0/SR/samples/jingkun-2018/jingkun_up.wav
Binary file not shown.
Binary file removed speechV2.0/SR/samples/test-2018/test_down.wav
Binary file not shown.
Binary file removed speechV2.0/SR/samples/test-2018/test_left.wav
Binary file not shown.
Binary file removed speechV2.0/SR/samples/test-2018/test_up.wav
Binary file not shown.
Binary file removed speechV2.0/SR/samples/test.wav
Binary file not shown.
Binary file removed speechV2.0/SR/samples/zhi-2018/zhi_down.wav
Binary file not shown.
Binary file removed speechV2.0/SR/samples/zhi-2018/zhi_left.wav
Binary file not shown.
Binary file removed speechV2.0/SR/samples/zhi-2018/zhi_up.wav
Binary file not shown.
1 change: 0 additions & 1 deletion speechV2.0/SR/scikittest.py

This file was deleted.

Loading

0 comments on commit afde08f

Please sign in to comment.