Merge pull request #13 from codeforequity-at/develop

Version 1.0.0

.env

@@ -1 +1,2 @@
 COMPOSE_PROJECT_NAME=botiumspeechprocessing
+TAG=latest

.env.develop

@@ -0,0 +1,2 @@
+COMPOSE_PROJECT_NAME=botiumspeechprocessing
+TAG=develop

.gitignore

@@ -1 +1,2 @@
-logs
+logs
+docker-compose.override.yml

Makefile

@@ -0,0 +1,53 @@
+TAG_COMMIT := $(shell git rev-list --abbrev-commit --tags --max-count=1)
+VERSION := $(shell git describe --abbrev=0 --tags ${TAG_COMMIT} 2>/dev/null || true)
+
+docker_build_develop:
+	docker build -t botium/botium-speech-frontend:develop frontend
+	docker build -t botium/botium-speech-watcher:develop watcher
+	docker build -f stt/Dockerfile.kaldi.en -t botium/botium-speech-kaldi-en:develop stt
+	docker build -f stt/Dockerfile.kaldi.de -t botium/botium-speech-kaldi-de:develop stt
+	docker build -f tts/Dockerfile.marytts -t botium/botium-speech-marytts:develop tts
+	docker build -t botium/botium-speech-dictate:develop dictate
+
+docker_publish_develop:
+	docker push botium/botium-speech-frontend:develop
+	docker push botium/botium-speech-watcher:develop
+	docker push botium/botium-speech-kaldi-en:develop
+	docker push botium/botium-speech-kaldi-de:develop
+	docker push botium/botium-speech-marytts:develop
+	docker push botium/botium-speech-dictate:develop
+
+docker_build_release:
+	docker build -t botium/botium-speech-frontend:$(VERSION) frontend
+	docker build -t botium/botium-speech-watcher:$(VERSION) watcher
+	docker build -f stt/Dockerfile.kaldi.en -t botium/botium-speech-kaldi-en:$(VERSION) stt
+	docker build -f stt/Dockerfile.kaldi.de -t botium/botium-speech-kaldi-de:$(VERSION) stt
+	docker build -f tts/Dockerfile.marytts -t botium/botium-speech-marytts:$(VERSION) tts
+	docker build -t botium/botium-speech-dictate:$(VERSION) dictate
+
+docker_publish_release:
+	docker push botium/botium-speech-frontend:$(VERSION)
+	docker push botium/botium-speech-watcher:$(VERSION)
+	docker push botium/botium-speech-kaldi-en:$(VERSION)
+	docker push botium/botium-speech-kaldi-de:$(VERSION)
+	docker push botium/botium-speech-marytts:$(VERSION)
+	docker push botium/botium-speech-dictate:$(VERSION)
+
+docker_latest_release:
+	docker tag botium/botium-speech-frontend:$(VERSION) botium/botium-speech-frontend:latest
+	docker push botium/botium-speech-frontend:latest
+
+	docker tag botium/botium-speech-watcher:$(VERSION) botium/botium-speech-watcher:latest
+	docker push botium/botium-speech-watcher:latest
+
+	docker tag botium/botium-speech-kaldi-en:$(VERSION) botium/botium-speech-kaldi-en:latest
+	docker push botium/botium-speech-kaldi-en:latest
+
+	docker tag botium/botium-speech-kaldi-de:$(VERSION) botium/botium-speech-kaldi-de:latest
+	docker push botium/botium-speech-kaldi-de:latest
+
+	docker tag botium/botium-speech-marytts:$(VERSION) botium/botium-speech-marytts:latest
+	docker push botium/botium-speech-marytts:latest
+
+	docker tag botium/botium-speech-dictate:$(VERSION) botium/botium-speech-dictate:latest
+	docker push botium/botium-speech-dictate:latest

README.md

@@ -6,11 +6,6 @@
 
 Botium Speech Processing is a unified, developer-friendly API to the best available free and Open-Source Speech-To-Text and Text-To-Speech services.
 
-**UPDATE 2020/06/15:** As Chatbots grow in importance, automated testing solutions will remain critical for ensuring that Chatbots actually do what their designers intend. We've been busy working on a product that allows testers to have visual insights and deeper understanding in their Chatbot's performance, offering several solutions to boost their interaction!
-[Botium Coach will be introduced to the market as part of our online event on the 24th of June.](https://www.botium.ai/coach/)
-
-[![](http://img.youtube.com/vi/WsNaDfZ7WHk/0.jpg)](http://www.youtube.com/watch?v=WsNaDfZ7WHk "Botium Coach is coming on 24th of June")
-
 ## What is it ?
 
 Botium Speech Processing is a *get-shit-done*-style Open-Source software stack, the configuration options are rudimentary: it is highly opinionated about the included tools, just get the shit done.
@@ -49,10 +44,11 @@ Clone or download this repository and start with docker-compose:
 
     > docker-compose up -d
 
-This will download the prebuilt images from Dockerhub.
+This will download the latest released prebuilt images from Dockerhub. To download the latest developer images from Dockerhub:
 
-Point your browser to http://127.0.0.1 to open the [Swagger UI](https://swagger.io/tools/swagger-ui/) and browse/use the API definition.
+    > docker-compose --env-file .env.develop up
 
+Point your browser to http://127.0.0.1 to open the [Swagger UI](https://swagger.io/tools/swagger-ui/) and browse/use the API definition.
 
 ### Optional: Build Docker Images
 
@@ -158,6 +154,12 @@ This project is standing on the shoulders of giants.
 
 ## Changelog
 
+### 2020-12-18
+
+* Adding support for Google Text-To-Speech
+* Adding support for listing and using available TTS voices
+* Added sample docker-compose configurations for PicoTTS and Google
+
 ### 2020-03-05
 
 * Optional _start_/_end_ parameters for audio file conversion to trim an audio file by time codes formatted as mm:ss (_01:32_)

dictate/Dockerfile

@@ -11,4 +11,5 @@ RUN curl -L -o dicatejs.zip "https://github.com/Kaljurand/dictate.js/archive/mas
 
 EXPOSE 56100
 
+USER node
 CMD DICTATEDIR=/app/dictate.js-master npm start

docker-compose-dev.yml

@@ -10,12 +10,14 @@ services:
   frontend:
     build:
       context: frontend
+    image: botium/botium-speech-frontend:develop
     restart: always
     volumes:
       - "./frontend/resources:/app/resources"
   watcher:
     build:
       context: watcher
+    image: botium/botium-speech-watcher:develop
     restart: always
     volumes:
       - "./watcher:/app/watch"
@@ -24,22 +26,26 @@ services:
     build:
       context: stt
       dockerfile: Dockerfile.kaldi.en
+    image: botium/botium-speech-kaldi-en:develop
     restart: always
     volumes:
       - "./logs/stt_en:/opt/logs"
   stt_de:
     build:
       context: stt
       dockerfile: Dockerfile.kaldi.de
+    image: botium/botium-speech-kaldi-de:develop
     restart: always
     volumes:
       - "./logs/stt_de:/opt/logs"
   tts:
     build:
       context: tts
       dockerfile: Dockerfile.marytts
+    image: botium/botium-speech-marytts:develop
     restart: always
   dictate:
     build:
       context: dictate
+    image: botium/botium-speech-dictate:develop
     restart: always

docker-compose-google.yml

@@ -0,0 +1,26 @@
+version: '3'
+services:
+  nginx:
+    image: nginx
+    restart: always
+    volumes:
+      - ./nginx.conf:/etc/nginx/nginx.conf
+    ports:
+      - 80:80
+  frontend:
+    image: botium/botium-speech-frontend:latest
+    restart: always
+    environment:
+      BOTIUM_API_TOKENS: 
+      BOTIUM_SPEECH_PROVIDER_TTS: google
+      BOTIUM_SPEECH_PROVIDER_STT: google
+      BOTIUM_SPEECH_GOOGLE_CLIENT_EMAIL:
+      BOTIUM_SPEECH_GOOGLE_PRIVATE_KEY:
+    volumes:
+      - "./frontend/resources:/app/resources"
+  watcher:
+    image: botium/botium-speech-watcher:latest
+    restart: always
+    volumes:
+      - "./watcher:/app/watch"
+      - "./logs/watcher:/app/logs"

docker-compose-picotts.yml

@@ -0,0 +1,37 @@
+version: '3'
+services:
+  nginx:
+    image: nginx
+    restart: always
+    volumes:
+      - ./nginx.conf:/etc/nginx/nginx.conf
+    ports:
+      - 80:80
+  frontend:
+    image: botium/botium-speech-frontend:latest
+    restart: always
+    environment:
+      BOTIUM_API_TOKENS: 
+      BOTIUM_SPEECH_PROVIDER_TTS: picotts
+      BOTIUM_SPEECH_PROVIDER_STT: kaldi
+    volumes:
+      - "./frontend/resources:/app/resources"
+  watcher:
+    image: botium/botium-speech-watcher:latest
+    restart: always
+    volumes:
+      - "./watcher:/app/watch"
+      - "./logs/watcher:/app/logs"
+  stt_en:
+    image: botium/botium-speech-kaldi-en:latest
+    restart: always
+    volumes:
+      - "./logs/stt_en:/opt/logs"
+  stt_de:
+    image: botium/botium-speech-kaldi-de:latest
+    restart: always
+    volumes:
+      - "./logs/stt_de:/opt/logs"
+  dictate:
+    image: botium/botium-speech-dictate:latest
+    restart: always

docker-compose.override.template.yml

@@ -0,0 +1,7 @@
+version: '3'
+services:
+  dictate:
+    image: botium/botium-speech-dictate:develop
+    environment:
+      STT_URL_DE: wss://speech.botiumbox.com/stt_de
+      STT_URL_EN: wss://speech.botiumbox.com/stt_en

docker-compose.yml

@@ -8,29 +8,35 @@ services:
     ports:
       - 80:80
   frontend:
-    image: botium/botium-speech-frontend:latest
+    image: botium/botium-speech-frontend:${TAG}
     restart: always
+    environment:
+      BOTIUM_API_TOKENS: 
+      BOTIUM_SPEECH_PROVIDER_TTS: marytts
+      BOTIUM_SPEECH_PROVIDER_STT: kaldi
+      BOTIUM_SPEECH_GOOGLE_CLIENT_EMAIL:
+      BOTIUM_SPEECH_GOOGLE_PRIVATE_KEY:
     volumes:
       - "./frontend/resources:/app/resources"
   watcher:
-    image: botium/botium-speech-watcher:latest
+    image: botium/botium-speech-watcher:${TAG}
     restart: always
     volumes:
       - "./watcher:/app/watch"
       - "./logs/watcher:/app/logs"
   stt_en:
-    image: botium/botium-speech-kaldi-en:latest
+    image: botium/botium-speech-kaldi-en:${TAG}
     restart: always
     volumes:
       - "./logs/stt_en:/opt/logs"
   stt_de:
-    image: botium/botium-speech-kaldi-de:latest
+    image: botium/botium-speech-kaldi-de:${TAG}
     restart: always
     volumes:
       - "./logs/stt_de:/opt/logs"
   tts:
-    image: botium/botium-speech-marytts
+    image: botium/botium-speech-marytts:${TAG}
     restart: always
   dictate:
-    image: botium/botium-speech-dictate
+    image: botium/botium-speech-dictate:${TAG}
     restart: always

frontend/Dockerfile

@@ -1,15 +1,19 @@
 FROM ubuntu:18.04
 
 RUN apt-get update && apt-get -y install curl gnupg && curl -sL https://deb.nodesource.com/setup_14.x  | bash - && apt-get -y install nodejs
-RUN apt-get install -y dos2unix sox libsox-fmt-mp3 libttspico-utils
+RUN apt-get update && apt-get install -y dos2unix sox libsox-fmt-mp3 libttspico-utils ffmpeg
 
 WORKDIR /app
-COPY . /app
-RUN find . -type f -print0 | xargs -0 dos2unix
+COPY ./package.json /app/package.json
 RUN npm install --no-optional --production
+COPY . /app
+COPY ./resources/.env /app/.env
+RUN find . -type f ! -path '*/node_modules/*' -print0 | xargs -0 dos2unix
 
 VOLUME /app/resources
 
 EXPOSE 56000
 
-CMD npm start
+RUN groupadd --gid 1000 node && useradd --uid 1000 --gid node --shell /bin/bash --create-home node
+USER node
+CMD npm run start-dist

frontend/package.json

@@ -5,39 +5,41 @@
   "scripts": {
     "eslint": "eslint src",
     "eslint-fix": "eslint --fix src",
-    "start": "cross-env DOTENV_FLOW_PATH=./resources nodemon -w ./resources/.env -w ./resources/.env.local -w ./src/ -x \"node -r dotenv-flow/config\" ./src/server.js",
+    "start-dev": "cross-env DOTENV_FLOW_PATH=./resources nodemon -w ./resources/.env -w ./resources/.env.local -w ./src/ -x \"node -r dotenv-flow/config\" ./src/server.js",
+    "start-dist": "node -r dotenv-flow/config ./src/server.js",
     "jsdoc": "swagger-jsdoc -d ./src/swaggerDef.json -o ./src/swagger.json src/routes.js"
   },
   "author": "Botium GmbH",
   "license": "MIT",
   "dependencies": {
-    "@google-cloud/speech": "^3.6.0",
-    "@google-cloud/storage": "^4.3.0",
+    "@google-cloud/speech": "^4.1.5",
+    "@google-cloud/storage": "^5.7.0",
+    "@google-cloud/text-to-speech": "^3.1.3",
     "body-parser": "^1.19.0",
-    "cross-env": "^7.0.0",
-    "debug": "^4.1.1",
-    "dotenv-flow": "^3.1.0",
+    "cross-env": "^7.0.3",
+    "debug": "^4.3.1",
+    "dotenv-flow": "^3.2.0",
     "express": "^4.17.1",
-    "express-winston": "^4.0.1",
-    "lodash": "^4.17.15",
-    "mkdirp": "^0.5.1",
-    "mustache": "^3.1.0",
-    "nodemon": "^2.0.1",
-    "request": "^2.88.0",
-    "request-promise-native": "^1.0.8",
+    "express-winston": "^4.0.5",
+    "lodash": "^4.17.20",
+    "mkdirp": "^1.0.4",
+    "mustache": "^4.1.0",
+    "nodemon": "^2.0.6",
+    "request": "^2.88.2",
+    "request-promise-native": "^1.0.9",
     "sanitize-filename": "^1.6.3",
-    "swagger-jsdoc": "^3.5.0",
-    "swagger-ui-express": "^4.1.2",
-    "uuid": "^3.3.3",
-    "winston": "^3.2.1",
-    "word-error-rate": "0.0.7"
+    "swagger-jsdoc": "^6.0.0-rc.5",
+    "swagger-ui-express": "^4.1.5",
+    "uuid": "^8.3.2",
+    "winston": "^3.3.3",
+    "word-error-rate": "^0.0.7"
   },
   "devDependencies": {
-    "eslint": "^6.7.2",
-    "eslint-config-standard": "^14.1.0",
-    "eslint-plugin-import": "^2.19.1",
-    "eslint-plugin-node": "^10.0.0",
+    "eslint": "^7.15.0",
+    "eslint-config-standard": "^16.0.2",
+    "eslint-plugin-import": "^2.22.1",
+    "eslint-plugin-node": "^11.1.0",
     "eslint-plugin-promise": "^4.2.1",
-    "eslint-plugin-standard": "^4.0.1"
+    "eslint-plugin-standard": "^5.0.0"
   }
 }