This package contains functions for analysing language through the Google Cloud Machine Learning APIs
Note all are paid services, you will need to provide your credit card details for your own Google Project to use them.
The package can be used by any user who is looking to take advantage of Google’s massive dataset to train these machine learning models. Some applications include:
- Translation of speech into another language text, via speech-to-text then translation and having the results spoen back to you
- Talking Shiny apps
- Identification of sentiment within text, such as from Twitter feeds
- Pulling out the objects of a sentence, to help classify texts and get metadata links from Wikipedia about them.
The applications of the API results could be relevant to business or researchers looking to scale text analysis.
Google Natural Language API reveals the structure and meaning of text by offering powerful machine learning models in an easy to use REST API. You can use it to extract information about people, places, events and much more, mentioned in text documents, news articles or blog posts. You can also use it to understand sentiment about your product on social media or parse intent from customer conversations happening in a call center or a messaging app.
Read more on the Google Natural Language API
Google Cloud Translation API provides a simple programmatic interface for translating an arbitrary string into any supported language. Translation API is highly responsive, so websites and applications can integrate with Translation API for fast, dynamic translation of source text from the source language to a target language (e.g. French to English).
Read more on the Google Cloud Translation Website
Google Cloud Speech-to-Text API enables you to convert audio to text by applying neural network models in an easy to use API. The API recognizes over 80 languages and variants, to support your global user base. You can transcribe the text of users dictating to an application’s microphone or enable command-and-control through voice among many other use cases.
Read more on the Google Cloud Speech Website
Google Cloud Text-to-Speech enables developers to synthesize natural-sounding speech with 30 voices, available in multiple languages and variants. It applies DeepMind’s groundbreaking research in WaveNet and Google’s powerful neural networks to deliver the highest fidelity possible. With this easy-to-use API, you can create lifelike interactions with your users, across many applications and devices.
- Create a Google API Console Project
- Within your project, add a payment method to the project
- Within your project, check the relevant APIs are activated
- Google Natural Language API
- Google Cloud Translation API
- Google Cloud Speech-to-Text API
- Google Cloud Text-to-Speech API
- Generate a service account credential as a JSON file by first creating a service account and then creating credentials for a service account
- Return to R, and install the official release via
install.packages("googleLanguageR"), or the development version with
Some Docker images are publicly available. In general
gcr.io/gcer-public/googleLanguageR:$BRANCH_NAME carries that GitHub branch’s version.
The best way to authenticate is to use an environment file. See
?Startup. I usually place this in my home directory. (e.g. if using RStudio, click on
Home in the file explorer, create a new
TEXT file and call it
Set the file location of your download Google Project JSON file in a
Then, when you load the library you should auto-authenticate:
You can also authenticate directly using the
gl_auth function pointing at your JSON auth file:
You can then call the APIs via the functions:
The Natural Language API returns natural language understanding technolgies. You can call them individually, or the default is to return them all. The available returns are:
- Entity analysis - Finds named entities (currently proper names and common nouns) in the text along with entity types, salience, mentions for each entity, and other properties. If possible, will also return metadata about that entity such as a Wikipedia URL. If using the v1beta2 endpoint this also includes sentiment for each entity.
- Syntax - Analyzes the syntax of the text and provides sentence boundaries and tokenization along with part of speech tags, dependency trees, and other properties.
Sentiment - The overall sentiment of the text, represented by a magnitude
[0, +inf]and score between
-1.0(negative sentiment) and
You can pass a vector of text which will call the API for each element. The return is a list of responses, each response being a list of tibbles holding the different types of analysis.
You can detect the language via
gl_translate_detect, or translate and detect language via
Note this is a lot more refined than the free version on Google’s translation website.
text <- "to administer medicine to animals is frequently a very difficult matter, and yet sometimes it's necessary to do so"
## translate British into Danish
gl_translate(text, target = "da")$translatedText
See more examples and details on the website or via
vignette("translate", package = "googleLanguageR")
The Cloud Speech-to-Text API provides audio transcription. Its accessible via the
A test audio file is installed with the package which reads:
“To administer medicine to animals is frequently a very difficult matter, and yet sometimes it’s necessary to do so”
The file is sourced from the University of Southampton’s speech detection (
http://www-mobile.ecs.soton.ac.uk/newcomms/) group and is fairly difficult for computers to parse, as we see below:
## get the sample source file
test_audio <- system.file("woman1_wb.wav", package = "googleLanguageR")
## its not perfect but...:)
## # A tibble: 1 x 2
## transcript confidence
## <chr> <chr>
## 1 to administer medicine to animals is frequency of very diffi… 0.9180294
The Cloud Text-to-Speech API turns text into talk audio files. Its accessible via the
To use, supply your text to the function:
gl_talk("This is a talking computer. Hello Dave.")
See more examples and details on the website or via
vignette("text-to-speech", package = "googleLanguageR")