whisper_android and whisper-to-input
These are complementary tools: one provides a reusable TensorFlow Lite inference engine for offline Whisper on Android, while the other is a keyboard application that consumes speech-to-text functionality (potentially using similar underlying models) to enable direct text input.
About whisper_android
vilassn/whisper_android
Offline Speech Recognition with OpenAI Whisper and TensorFlow Lite for Android
This project offers pre-built Android apps and code examples to add offline speech recognition capabilities to Android devices. It takes spoken audio (like a voice recording) and converts it into text, all without needing an internet connection. This is for Android developers who want to integrate powerful speech-to-text features into their mobile applications.
About whisper-to-input
j3soon/whisper-to-input
An Android keyboard that performs speech-to-text (STT/ASR) with OpenAI Whisper and input the recognized text; Supports English, Chinese, Japanese, etc. and even mixed languages.
This Android keyboard translates spoken words into text, allowing you to quickly type messages, emails, or documents by just speaking. It supports many languages and can even handle mixed-language input. Anyone who regularly uses an Android device and wants to convert their speech into written text efficiently will find this useful.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work