IS2AI/TurkicASR
A multilingual ASR model that can recognize ten Turkic languages—Azerbaijani, Bashkir, Chuvash, Kazakh, Kyrgyz, Sakha, Tatar, Turkish, Uyghur, and Uzbek.
Built on ESPnet, the project combines multiple public datasets (KSC, TSC, USC, and Common Voice 10.0) to train multilingual end-to-end ASR models, with options for Turkic-only or polyglot training. Pre-trained models are provided for immediate inference on 16kHz WAV files via a simple command-line interface. The architecture supports both single-language and cross-lingual training strategies, enabling transfer learning across related Turkic language families.
No commits in the last 6 months.
Stars
82
Forks
11
Language
Python
License
CC-BY-4.0
Category
Last pushed
Aug 01, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/IS2AI/TurkicASR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
neosun100/Step-Audio-R1.1
Step-Audio-R1.1: The First Audio Language Model with Test-Time Compute Scaling. All-in-One...
Aditya1Jhaveri/AI-Video-Dubbing
AI video dubbing using Google APIs automates translation and dubbing by transcribing audio with...
seanpm2001/Phoneticut
Phoneticut is a voice actor replacement: Make a certain amount of sounds, and have stitching and...
WildCraftsmanFilter/AI-Voice-Changer-Real-Time-Desktop
⭐️ AI Voice-Changer Real-Time 2026 is advanced AI voice changer software powered by deep...
grayhatdevelopers/deepdub
🗣️ Videos for everyone. Implementation of "Automated Dubbing and Facial Synchronization using...