This is a fine-tuned version of OpenAI's Whisper model specialized for converting Hindi speech containing English words (Hinglish) into text. Built on the transformers library, it provides improved accuracy for code-mixed Indian language audio. It is intended for developers integrating multilingual speech recognition into applications.
Whisper Hindi2Hinglish Apex is a Voice, TTS & speech project. Accurately transcribing Hindi speech that mixes English words (Hinglish) using specialized ASR models. It is built as an open-source project for developers. Whisper Hindi2Hinglish Apex is open source under the Apache-2.0 license. It runs on the web and the command line, and it can be self-hosted.
It is developed by Oriserve, and it first shipped in 2025. The project is developed in the open on GitHub with 26 stars. Among its 3 catalogued features are speech recognition, hindi to Hinglish, and automatic transcription.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do