Updating vietnamese language and training model

README.md

@@ -41,40 +41,46 @@
 </p>
 
 ## Introduction
+
 <p align="center">
   <img alt="introduction" height="100" src="https://i.imgur.com/Ygm9CMc.png">
 </p>
 
 ### Description
+
 Olivia is an open-source chatbot built in Golang using Machine Learning technologies.
-Its goal is to provide a free and open-source alternative to big services like DialogFlow. 
+Its goal is to provide a free and open-source alternative to big services like DialogFlow.
 
 You can chat with her by speaking (STT) or writing, she replies with a text message but you can enable her voice (TTS).
 
 You can clone the project and customize it as you want using [GitHub](https://github.com/olivia-ai/olivia)
 Try it on [her website!](https://olivia-ai.org)
 
 ### Why Olivia?
+
 - The only chatbot project in Go that could be modulable and customizable.
 - Using daily a privacy-friendly chatbot is great.
 - The Website is a Progressive Web Application, which means you can add it to your phone and it seems like a native app!
 
-
 ## Getting started
-### Installation 
-#### Login to Github 
+
+### Installation
+
+#### Login to Github
 
 To get a personal access token from Github go to `Setings > Developer settings > Personal Access Tokens`
 
 Click on Generate new Token and name it you MUST have read and write packages ticked on.
 Then click Generate new token
 
 Replace `TOKEN` with the Token that you just made.
+
 ```bash
 $ export PAT=TOKEN
 ```
 
 Login to Github (Note: change USERNAME to Gthub username)
+
 ```bash
 $ echo $PAT | docker login docker.pkg.github.com -u USERNAME --password-stdin
 ```
@@ -86,57 +92,66 @@ $ echo $PAT | docker login docker.pkg.github.com -u USERNAME --password-stdin
 </p>
 
 Pull the image from GitHub Packages
+
 ```bash
 $ docker pull docker.pkg.github.com/olivia-ai/olivia/olivia:latest
 ```
 
 Then start it
+
 ```bash
 $ docker run -d -e PORT=8080 -p 8080:8080 docker.pkg.github.com/olivia-ai/olivia/olivia:latest
 ```
 
 You can just use the websocket of Olivia now.
 
 To stop it, get the container id:
+
 ```bash
 $ docker container ls
 ```
+
 ```bash
 CONTAINER ID        IMAGE               COMMAND             CREATED             STATUS              PORTS                    NAMES
 311b3abb963a        olivia              "./main"            7 minutes ago       Up 7 minutes        0.0.0.0:8080->8080/tcp   quizzical_mayer
 ```
 
 and stop it
+
 ```bash
-$ docker container stop 311b3abb963a 
+$ docker container stop 311b3abb963a
 ```
 
 The app will automatically check for `res/datasets/training.json` file which contains the save of the neural network.
 By default when you clone the repository from Github you have a stable save.
 If you want to train a new model just delete this file and rerun the app.
 
 #### GitHub
+
 <p align="center">
   <img height="100" src="https://i.imgur.com/RRPoP69.png">
 </p>
 
 Clone the project via GitHub:
 
-```bash 
+```bash
 $ git clone [email protected]:olivia-ai/olivia.git
 ```
 
 Then download the dependencies
+
 ```bash
 $ go mod download
 ```
 
 And run it
+
 ```bash
 $ go run main.go
 ```
 
 ### Frontend and Backend
+
 To install the frontend and the backend together, please use the `docker-compose.yml` file:
 
 ```bash
@@ -146,6 +161,7 @@ $ docker-compose up
 And all done!
 
 ## Architecture
+
 <p align="center">
   <img alt="architecture" height="85" src="https://i.imgur.com/95h8WIU.png">
   <br>
@@ -159,15 +175,18 @@ And all done!
 </p>
 
 ### Languages supported
+
 - <img src="https://i.imgur.com/URqxsb0.png" width="25"> English
 - <img src="https://i.imgur.com/Oo5BNk0.png" width="25"> Spanish
 - <img src="https://i.imgur.com/2DWxeF9.png" width="25"> Catalan
 - <img src="https://i.imgur.com/0dVqbjf.png" width="25"> French
 - <img src="https://i.imgur.com/sXLQp8e.png" width="25"> German
 - <img src="https://i.imgur.com/DGNcrRF.png" width="25"> Italian
+- <img src="https://i.imgur.com/tq19CY1.png" width="25"> Vietnam
 - <img src="https://i.imgur.com/kB0RoFZ.png" width="25"> Brazilian portuguese - not completed
 
 ### Coverage
+
 The coverage of the translations is given [here](https://olivia-ai.org/dashboard/language).
 To add a language please read [the documentation for that](https://docs.olivia-ai.org/translations.html).
 
@@ -181,13 +200,14 @@ To add a language please read [the documentation for that](https://docs.olivia-a
 Please refer to the [contributing file](.github/CONTRIBUTING.md)
 
 ### Code Contributors
-Thanks to the people who contribute to Olivia. 
+Thanks to the people who contribute to Olivia.
 
 [Contribute](.github/CONTRIBUTING.md)
 <a href="https://github.com/olivia-ai/olivia/graphs/contributors"><img src="https://opencollective.com/olivia-ai/contributors.svg?width=950&button=false" /></a>
 
 ### Financial Contributors
-Become a financial contributor and help Olivia growth. 
+
+Become a financial contributor and help Olivia growth.
 
 Contribute on the GitHub page of [hugolgst](https://github.com/sponsors/hugolgst) ❤️
 

language/date/date.go

@@ -36,6 +36,10 @@ var PatternTranslation = map[string]PatternTranslations{
 		DateRegex: `(από )?(το )?((μεθ )?αύριο|((σήμερα|απόψε)|(επόμενη )?(δευτέρα|τρίτη|τετάρτη|πέμπτη|παρασκευή|σάββατο|κυριακή))|(\d{2}|\d)(η)? (of )?(ιανουάριος|φεβρουάριος|μάρτιος|απρίλιος|μάιος|ιούνιος|ιούλιος|αύγουστος|σεπτέμβριος|οκτώβριος|νοέμβριος|δεκέμβριος)|((\d{2}|\d)/(\d{2}|\d)))`,
 		TimeRegex: `(at )?(\d{2}|\d)(:\d{2}|\d)?( )?(μμ|πμ|μ\.μ|π\.μ)`,
 	},
+	"vi": {
+		DateRegex: `(của )?(một )?((sau )?ngày mai|((hôm nay|tối nay)|(tiếp )?(thứ hai|thứ ba|thứ tư|thứ năm|thứ sáu|thứ bảy|chủ nhật))|(\d{2}|\d)(th|rd|st|nd)? (of )?(january|february|march|april|may|june|july|august|september|october|november|december)|((\d{2}|\d)/(\d{2}|\d)))`,
+		TimeRegex: `(tại )?(\d{2}|\d)(:\d{2}|\d)?( )?(chiều|sáng|p\.m|a\.m)`,
+	},
 }
 
 // PatternTranslations are the translations of the regexs for dates

language/date/rules.go

@@ -119,6 +119,21 @@ var RuleTranslations = map[string]RuleTranslation{
 		RuleNextDayOfWeek: "επόμενη",
 		RuleNaturalDate:   `ιανουάριος|φεβρουάριος|μάρτιος|απρίλιος|μάιος|ιούνιος|ιούλιος|αύγουστος|σεπτέμβριος|οκτώβριος|νοέμβριος|δεκέμβριος`,
 	},
+	"vi": {
+		DaysOfWeek: []string{
+			"thứ hai", "thứ ba", "thứ tư", "thứ năm", "thứ sáu", "thứ bảy", "chủ nhật",
+		},
+		Months: []string{
+			"tháng 1", "tháng 2", "tháng 3", "tháng 4", "tháng 5", "tháng 6", "tháng 7",
+			"tháng 8", "tháng 9", "tháng 10", "tháng 11", "tháng 12",
+		},
+		RuleToday:         `today|tonight`,
+		RuleTomorrow:      `(after )?tomorrow`,
+		RuleAfterTomorrow: "after",
+		RuleDayOfWeek:     `(next )?(thứ hai|thứ ba|thứ tư|thứ năm|thứ sáu|thứ bảy|chủ nhật)`,
+		RuleNextDayOfWeek: "next",
+		RuleNaturalDate:   `tháng 1|tháng 2|tháng 3|tháng 4|tháng 5|tháng 6|tháng 7|tháng 8|tháng 9|tháng 10|tháng 11|tháng 12`,
+	},
 }
 
 // A RuleTranslation is all the texts/regexs to match the dates

language/math.go

@@ -16,6 +16,7 @@ var MathDecimals = map[string]string{
 	"it": `(\d+( |-)decimale(s)?)|(numero (di )?decimale(s)? (è )?\d+)`,
 	"tr": `(\d+( |-)desimal(s)?)|(numara (dan )?desimal(s)? (mı )?\d+)`,
 	"nl": `(\d+( |-)decimal(en)?)|(nummer (van )?decimal(en)? (is )?\d+)`,
+	"vi": `(\d+( |-)decimal(s)?)|(nummer (van )?decimal(s)? (is )?\d+)`,
 	"el": `(\d+( |-)δεκαδικ(ό|ά)?)|(αριθμός (από )?δεκαδικ(ό|ά)? (είναι )?\d+)`,
 }
 

language/movies.go

@@ -57,6 +57,10 @@ var (
 			"Δράση", "Περιπέτεια", "Κινούμενα Σχέδια", "Παιδικά", "Κωμωδία", "Έγκλημα", "Ντοκιμαντέρ", "Δράμα", "Φαντασία",
 			"Film-Noir", "Τρόμου", "Μουσική", "Μυστηρίου", "Ρομαντική", "Επιστημονική Φαντασία", "Θρίλλερ", "Πολέμου", "Western",
 		},
+		"vi": {
+			"Hành động", "Thám hiển", "Hoạt hình", "Trẻ em", "Hài hước", "Tội phạm", "Phim tài liệu", "Kịch", "Viễn tưởng",
+			"Film-Noir", "Kinh dị", "Âm nhạc", "Bí ẩn", "Lãng mạn", "Khoa học - Viễn tưởng", "Giật gân", "Chiến tranh", "Western",
+		},
 	}
 	movies = SerializeMovies()
 )

language/music.go

@@ -51,6 +51,11 @@ var SpotifyKeyword = map[string]SpotifyKeywords{
 		From: "από",
 		On:   "στο",
 	},
+	"vi": {
+		Play: "Chạy",
+		From: "Từ",
+		On:   "Bật",
+	},
 }
 
 // SpotifyKeywords are the keywords used to get music name

language/reason.go

@@ -42,6 +42,10 @@ var ReasonKeywords = map[string]ReasonKeyword{
 		That: "το οποίο",
 		To:   "στο",
 	},
+	"vi": {
+		That: "Đây là",
+		To:   "Tới",
+	},
 }
 
 // ReasonKeyword are used to find reason for different languages

locales/locales.go

@@ -11,8 +11,7 @@ import (
 	_ "github.com/olivia-ai/olivia/res/locales/it"
 	_ "github.com/olivia-ai/olivia/res/locales/nl"
 	_ "github.com/olivia-ai/olivia/res/locales/tr"
-	_ "github.com/olivia-ai/olivia/res/locales/el"
-
+	_ "github.com/olivia-ai/olivia/res/locales/vi"
 )
 
 // Locales is the list of locales's tags and names
@@ -55,6 +54,10 @@ var Locales = []Locale{
 		Tag:  "el",
 		Name: "greek",
 	},
+	{
+		Tag:  "vi",
+		Name: "vietnam",
+	},
 }
 
 // A Locale is a registered locale in the file

res/datasets/countries.json

@@ -3842,5 +3842,23 @@
     "capital": "Harare",
     "area": 390757,
     "currency": "ZWL"
+  },
+  {
+    "name": {
+      "en": "Ha Noi",
+      "fr": "Ha Noi",
+      "es": "Ha Noi",
+      "ca": "Ha Noi",
+      "de": "Ha Noi",
+      "cn": "河内",
+      "pt": "Ha Noi",
+      "it": "Ha Noi",
+      "tr": "Ha Noi",
+      "nl": "Ha Noi",
+      "el": "Ханой"
+    },
+    "capital": "Harare",
+    "area": 390757,
+    "currency": "ZWL"
   }
 ]