Chinar is not a multilingual model with Azerbaijani bolted on, and not Turkish with an accent. The language is what it was built around — which is the difference between a transcript you can act on and one that merely looks finished.
Most speech engines treat Azerbaijani as a neighbouring case of a language they already handle, and the output reads fluently enough that nobody checks it. Chinar is built for Azerbaijani itself, in two sizes that share the same command of the language: Chinar-L for transcripts people read, Chinar-F for transcripts machines read. Both run on your own infrastructure.
Azerbaijani is the design target, not a language code passed to a general model.
Two sizes share the same language expertise, so their transcripts agree.
Chinar-L scores 87% word accuracy on clear Azerbaijani speech, measured against reference transcripts from a commercial speech system.
Trained on genuine call-centre recordings rather than read speech.
Runs on your own infrastructure, with no audio sent to a third party.
Chinar is built for Azerbaijani from the ground up rather than adapted from a related language.
Chinar-L reaches 87% word accuracy on clear Azerbaijani speech, measured against reference transcripts from a commercial speech system. Noisier audio scores lower.
Chinar-L when a person reads the transcript; Chinar-F when the volume matters more than the punctuation.
Chinar-L returns punctuated, capitalised Azerbaijani, ready for a document or a compliance record.
Chinar-F is roughly fifty times smaller — transcribe every call, not a sample.
Global services asked for Azerbaijani give back confident Turkish that looks like a working transcript.
Recordings stay on your infrastructure: no metering, no third-party retention.
See the complete product: problem, features, how it works and deployment.
Request a demo and we will run Chinar against your own Azerbaijani audio — Chinar-L for the transcript people read, Chinar-F for the volume.