Fact · Languages and accents
2languages
KaanAydinli's model card describes Duyu-small as a Turkish and English speech recognizer, so it recognizes 2 languages.
Quote found word for word on the live source, last checked October 22, 2026
- What it measures
- Duyu-small is an open speech recognition model on Hugging Face, shipped as ONNX graphs for CPUs and edge devices. The card says it writes whatever is spoken, Turkish, English or both in one sentence, and lists the language options tr, en, mix and auto.
- What it does not show
- The count is the two languages the card names. The mix and auto options are a mixed mode and automatic detection over those same two languages. The card reports no regional variants and no test on any other language.
In the data
A row of How Many Languages Speech Recognition Supports, as Duyu-small: 2 languages.
- System
- Duyu-small
- Maker
- KaanAydinli
- Kind
- Open model
- What is counted
- Languages
- On device
- Yes
- As of
- 2026-10
- Note
- The quote names two languages, Turkish and English, and the card names no others; num counts them.
Used to calculate
- In the languages supported by speech recognition systems dataset, the 69 published figures for “Open model” have a median of 25 languages, ranging from 1 to 1,672.
- The languages supported by speech recognition systems dataset holds 266 data points, each a published figure traced to its source.
- The languages supported by speech recognition systems dataset draws on 221 distinct sources.