Git Product home page Git Product logo

polyglot's Introduction

  • 👋 Hi, I’m @liou666

polyglot's People

Contributors

dadatom avatar liou666 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

polyglot's Issues

能否支持Vercel

Describe the problem you confuse

如果能支持Vercel就好了,就可以部署到Vercel,不需要自己的服务器就能访问了

[功能需求] 连续对话

Describe the problem you confuse

就是我想问一下能否实现连续对话功能呢?能实现的话那确实就感觉像是在对话

[Help] 帮忙看看是否能实现的需求

Describe the problem you confuse

1、支持多种格式的api key 不仅限于openai的key格式。
2、token数量是否能再增加?
3、能否在单一语种对话环境内增加一个临时切换输入语言的功能?当有问题不知道如用外语表达想让gpt翻译的时候使用
4、是否能实现单独选词发音练习读音功能
5、是否能实现单独选择某句实现翻译功能?
6、希望加一个结束某一个语种语音输入的功能按钮,比如我们和英文AI对话完之后,有个按钮结束英文环境,然后切换到日语,就能识别我们说的日语。
7、希望加一个我们一次语音说完之后的结束词功能,说一个特定的词,像Siri唤醒功能一样,结束此次语音输入并自动发送。
8、希望加一个能回听我们说的语音的功能,这样能回查自己的口语哪里有问题。

[Bug] replay audio

Describe the bug

点击语音播放按钮的时候,声音没播完的情况下,再点一次,播放会加入队列,点击几次会连续播放几次。按常见的UI交互方式,应该点第二次停止播放。每次播放队列中仅存一条语音。besides, 不知道有没有本地缓存机制

[Help] 为什么录音录不上?

Describe the problem you confuse

下了mac版,设置了api key,文字沟通可以,录音功能一直卡住,然后报错,请问使用录音功能需要设置代理吗?
image
image

[建议] api地址

添加baseURL设置

很nice的作品,有个小建议,现在由于OpenAI的封禁,很难去直接付费OpenAI的官方接口。所以:

能否添加API请求的baseURL设置(包括我在内的很多人都是通过第三方套壳API来调用OpenAI服务的)

建议开发手机客户端

现在这个软件太棒了。我每天都能感受到学习英语的乐趣了。但是由于没有手机客户端,只能开电脑训练。可以看下call annie这款APP,已经可以在手机上运行了。但是call annie不能定制功能。

[Help] how to read your code, and contribute?

How to read your code to understand the logical flow of the front-back end?
Can you show us an easy way to contribute to your code?

I'm a language learner, targeting at improving TOEFL speaking.
I'd like to implement an evaluation of AI for my answer, to improve my speaking. For example, after I respond to AI's question, AI could give me two replies, the first is the next question, and the second is the evaluation of my speaking.

How can I modify your code in an easy way to achieve my goal? Thanks a lot!

[建议] 希望能自定义语法检查功能的prompt

image
小灯泡点击之后,似乎只能进行语法检查

建议:

  1. 希望能自定义这个prompt,比如有时候想让ai给出几个更加地道的改进版本,或者是让ai换种表达风格之类的。
  2. 希望能给ai的聊天框也加上这个功能,同样是自定义prompt,这样就可以一键总结ai句子里的知识点,或者进行语法分析,生词积累等。

创建bot时能自定义这些,应该可以让学习更加灵活,学习方式更丰富👍🏻

[Help] SPACE - Keyboard shortcuts

Describe the feature I hope

I hope the SPACE button keyboard shortcuts.
Press-and-hold SPACE (outside text input) to record, and release to submit.

[Help] Want new function of play the audio of my input

Describe the problem you confuse

Hi lion666,

Your program is excellent. I am using it to practice my pronunciation for a presentation. Duo to some UI display problems in the sourse-code based version on my computer, I am still using the release v0.1.1.

I am wandering if there will be a new feature that allow me to play my input in azure tts. Although the recognition of my voice is very accurate, as a user, my pronunciation and tone are not always excellent. It would be more helpful for English practice if I could hear how a text-to-speech (TTS) system speaks the content of my input.

thanks
scaactk

[Bug] the title of bug report

polyglot-1 polyglot-2 请问我已经配置了GPT和Azure的Key,为什么出现图片中的错误。没有生成语音回答呢?

我用的是Mac版,也试了Web版,都是同样的错误。谢谢。

请求新增Azure TTS语言的选择 和 azure语音识别流式输出

Describe the problem you confuse

  1. azure tts可以选择对应的语言, 有时候我想用polyglot语音输入中文, 但是输出的总是牛头不对马嘴的英文. 希望可以添加选择语音识别语言的选项.
  2. 贵软件的语音识别在点击录音后开始, 如果要看到语音识别的结果, 需要再次点击录音键. 在实际使用中, 这种方式是非常不方便的, 因为不知道自己哪些声音录了进去, 有可能录了一些杂音. 我希望添加语音识别流式输出的功能, 就是在语音识别的过程中就可以把语音识别的结果输出出来, 而不是录完了再输出. 通俗点说, 就是用户说的过程中就可以看到语音输出的结果.

[Feature] 兼容api2d接口

Describe the problem you confuse

大佬我想给女朋友用,我现在的openai api用的是api2d的,代理选它的填api填它的,在你这好像不能用,它api格式好像不一样,其他软件就是正常填上去代理改好就好了。
这里提示输入正确的apikey是不是限制了格式呀,那个跟官方的不太一样,大佬能不能去掉限制打包一个版本。(个人觉得是这个原因又不会弄)
谢谢啦˃ʍ˂

【建议】预置场景

建议预置一些场景,每次对话要在一个场景中解决具体的问题。这样对话练习才更有目的性,和针对性。
不然漫无目的的瞎聊,其实得不到什么提升。

场景比如:

  • 你要向一位新员工介绍公司,直到员工满意为止。
  • 你要买一件衣服,你的任务是把价格从 100 美元 还到 50 美元。
    等等等等。

每次对话,都要解决具体的问题。让ai 故意刁难练习者。

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.