Language models

A language model is a neural network that is trained on phrases typical for a particular topic. For example, the Numbers model is the best choice for phone number recognition, while a person's first and last name are best recognized using the Names model.

The models are trained on datasets generated by Yandex services and applications. This allows us to continually improve the quality of speech recognition.

Supported language models

  • Queries (general) — Short phrases containing 3-5 words on various topics, including search engine or website queries. For example:
    • покажи следующий поворот
    • соединить с отделом продаж
    • еще чашку кофе и две мягких французских булочки
    • какая погода во владивостоке
    • напомни купить овощей и фруктов по дороге домой
  • Addresses (maps) — Addresses and names of companies or geographical features:
    • поехали на улицу кирпичные выемки пять
    • сколько ехать от льва толстого до новой земли
    • покажи маршрут до музея маяковского
  • Dates (dates) — Names of months, ordinal numbers, and cardinal numbers:
    • второго ноль седьмого две тысячи первого
    • двадцать седьмое апреля тысяча девятьсот девятнадцатого года
  • Names (names) — First and last names and phone call requests:
    • щукин платон
    • соедините с людчиком
    • переговорить с васей васиным
  • Numbers (numbers) — Cardinal numbers from 1 to 999 and delimiters (dot, comma, and dash). This model can be used to dictate phone numbers, account numbers, or document numbers:
    • два двенадцать восемьдесят пять ноль шесть
    • сто пятьдесят семь запятая пятнадцать сорок три
  • Queries (general) — Short phrases containing 3-5 words on various topics, including search engine or website queries:
    • connect me to the sales department
    • another cup of coffee and two soft French rolls
  • Addresses (maps) — Addresses and names of companies or geographical features:
    • go to Abbey Road
  • Queries (general) — Short phrases containing 3-5 words on various topics, including search engine or website queries:
    • satış departmanıyla görüşmek istiyorum
    • bir kahve daha ve iki küçük kurabiye
  • Addresses (maps) — Addresses and names of companies or geographical features:
    • Atatürk Bulvarı'na git