There are 24 new languages and dialects to Translate, Google announced on Wednesday. The new items added to the multilingual neural machine translation service include languages from different regions globally, including Quechua, Guarani, and Aymara, which are considered indigenous languages of the Americas. This brings the total number of languages covered by Google Translate to 133.
“For years, Google Translate has helped break down language barriers and connect communities all over the world. And we want to make this possible for even more people — especially those whose languages aren’t represented in most technology. So today we’ve added 24 languages to Translate, now supporting a total of 133 used around the globe,” says Google Translate Senior Software Engineer Isaac Caswell. “Over 300 million people speak these newly added languages — like Mizo, used by around 800,000 people in the far northeast of India, and Lingala, used by over 45 million people across Central Africa.”
Caswell notes that this latest update for Google Translate is rather special, given the languages are the first to be added using “Zero-Shot Machine Translation.” According to him, the machine learning model for these languages “learns to translate into another language without ever seeing an example” and “only sees monolingual text.” With this, the software engineer admits that it is not perfect in all manner, albeit he takes it as something impressive. “And we’ll keep improving these models to deliver the same experience you’re used to with a Spanish or German translation, for example,” he adds. “If you want to dig into the technical details, check out our Google AI blog post and research paper.”
Here is the complete list of the latest languages and dialects added to Google Translate, together with the locations where they are spoken and the number of speakers using them:
Assamese. Northeast India (about 25 million speakers)
Aymara. Bolivia, Chile, and Peru (about two million speakers)
Bambara. Mali (about 14 million speakers)
Bhojpuri. Northern India, Nepal, and Fiji (about 50 million speakers)
Dhivehi. Maldives (about 300,000 speakers)
Dogri. Northern India (about three million speakers)
Ewe. Ghana and Togo (about seven million speakers)
Guarani. Paraguay and Bolivia, Argentina and Brazil (about seven million speakers)
Ilocano. Northern Philippines (about 10 million speakers)
Konkani. Central India (about two million speakers)
Krio. Sierra Leone (about four million speakers)
Kurdish (Sorani). Iraq and Iran (about 15 million speakers)
Lingala. Democratic Republic of the Congo, Republic of the Congo, Central African Republic, Angola, and the Republic of South Sudan (about 45 million speakers)
Luganda. Uganda and Rwanda (about 20 million speakers)
Maithili. Northern India (about 34 million speakers)
Meiteilon (Manipuri). Northeast India (about two million speakers)
Mizo. Northeast India (about 830,000 speakers)
Oromo. Ethiopia and Kenya (about 37 million speakers)
Quechua. Peru, Bolivia, Ecuador, and surrounding countries (about 10 million speakers)
Sanskrit. India (about 20,000 speakers)
Sepedi. South Africa (about 14 million speakers)
Tigrinya. Eritrea and Ethiopia (about eight million speakers)
Tsonga. Eswatini, Mozambique, South Africa, and Zimbabwe (about seven million speakers)
Twi. Ghana (about 11 million speakers)