Central Kurdish (Sorani) Speech to Text: A Complete Guide
Central Kurdish (Sorani) Speech to Text: Breaking Barriers for a Rich Language
Central Kurdish, also known as Sorani (کوردیی ناوەندی), is the second most widely spoken Kurdish dialect after Kurmanji. It is the official language of the Kurdistan Region of Iraq and is used in government, education, media, and literature. With over 15 million speakers, Sorani is a vital language for Kurdish identity, yet it has been largely overlooked by mainstream speech recognition tools. Speechyou changes that.
Where Sorani Kurdish is Spoken
Sorani Kurdish is predominantly spoken in the Kurdistan Region of Iraq (provinces of Erbil, Sulaymaniyah, and Halabja) and in the Iranian provinces of Kordestan, West Azerbaijan, and Kermanshah. It is also used by the Kurdish diaspora in Europe, North America, and Australia. The language is written in a modified Arabic script (right-to-left) and has a rich literary tradition dating back to the 16th century.
The Challenge of Transcribing Sorani Kurdish
Accurate speech-to-text for Sorani Kurdish faces several hurdles:
- Arabic script with extra characters: The Sorani alphabet includes 33 letters, many of which are not found in Arabic. Short vowels (a, i, u) are usually omitted in writing, making transcription from audio a guessing game for ASR systems.
- Dialect diversity: The major dialects — Sulaymaniyah, Erbil, Mukri, and Warmawa — differ in pronunciation, vocabulary, and even grammar. A model trained on one dialect may fail on another.
- Code-switching: Many Sorani speakers mix Kurdish with Arabic, Persian, or English, especially in urban areas. This requires a multilingual ASR model.
Speechyou addresses these challenges directly. Our Sorani Kurdish model is trained on thousands of hours of speech from all major dialects, and it is designed to handle the Arabic script with diacritics, as well as code-switching. The result is a transcription accuracy of over 95% on clear audio.
Use Cases for Sorani Kurdish Speech-to-Text
1. Kurdish Media and News News channels like Rudaw, Kurdistan24, and NRT produce daily content in Sorani. Speechyou can transcribe interviews, reports, and talk shows, generating subtitles instantly. This helps broadcasters save time and reach a broader audience.
2. Oral History and Cultural Preservation Kurdish oral traditions are rich, with stories, songs, and poems passed down through generations. Speechyou allows researchers to convert audio recordings of elders into text, creating searchable archives that preserve the language for future generations.
3. Education and E-Learning Kurdish-language schools and universities can use Speechyou to transcribe lectures, provide subtitles for video courses, and create study materials for students. This is especially important for learners who are deaf or hard of hearing.
4. Accessibility By providing real-time captions and subtitles, Speechyou makes Kurdish content accessible to the deaf and hard of hearing community. This is a crucial step towards inclusivity.
5. Podcast and Audio Content Podcasting is growing in Kurdish communities. Speechyou enables podcasters to turn their episodes into written transcripts, which can be used for show notes, SEO, and social media sharing.
How Speechyou Helps
Speechyou is the first fully automated transcription service to offer dedicated support for Sorani Kurdish. Here’s what sets us apart:
- Native script support: Output is in the Arabic script, with correct right-to-left layout and special characters.
- Dialect-aware models: We have separate models for major dialects, ensuring high accuracy regardless of the speaker’s origin.
- Fast and affordable: With unlimited transcription included in the Solo plan, you can transcribe as much audio as you need.
- Export to SRT, VTT, TXT, and more: Generate subtitles for your videos or plain text transcripts for documentation.
Conclusion
Central Kurdish (Sorani) is a vibrant language with a rich cultural heritage. Until now, accurate speech-to-text for Sorani was a dream. Speechyou makes it a reality. Whether you are a journalist, educator, researcher, or content creator, our AI-powered transcription tool helps you convert Kurdish audio into text quickly and accurately. Try Speechyou today and experience the power of Kurdish speech recognition.
