Skip to content

Fact · Languages and accents

1languages

The speech.cpp model catalog lists one language, Japanese (ja), for the recognition model parakeet-tdt_ctc-0.6b-ja.

Quote found word for word on the live source, last checked October 22, 2026

In the source's own words

“Name Task Languages ... parakeet-tdt_ctc-0.6b-ja recognition ja”

speech.cpp: docs/models.md (model catalog, tasks and languages), nyosegawa, GitHub, nyosegawa/speech.cpp, 2026, Model table in docs/models.md, row parakeet-tdt_ctc-0.6b-ja.

Open the original
What it measures
speech.cpp is a speech program written in C++. Its model table lists parakeet-tdt_ctc-0.6b-ja for recognition, with the single language code ja.
What it does not show
The table gives a language code, not a count. One code is one language, Japanese.

In the data

A row of How Many Languages Speech Recognition Supports, as speech.cpp parakeet-tdt_ctc-0.6b-ja: 1 languages.

System
speech.cpp: parakeet-tdt_ctc-0.6b-ja
Maker
nyosegawa
Kind
Open model
What is counted
Languages
On device
Yes
As of
2026-10
Note
The table lists one language code, ja, so one language.

Source

Used to calculate