#145 · Primary category: Speech & Audio

whisper_android

android asr automatic-speech-recognition embedded mobile offline openai speech-recognition tensorflow tensorflowlite text-to-speech texttospeech tflite transcribe transcription translation tts whisper

Offline Speech Recognition with OpenAI Whisper and TensorFlow Lite for Android

Project last updated:03/18/26

GitHub Stars

688

Forks

111

Contributors

3

License

MIT

Why we included this project

Android developers who need speech-to-text that works without a network connection will find a working reference here. The repo packages OpenAI's Whisper into TensorFlow Lite and ships two complete apps, one built on the TFLite Java API for easy integration and one on the native API for better performance. A Python script converts Whisper checkpoints into TFLite models, and pre-built APKs let you try the apps before writing any code. The README documents the Whisper and Recorder classes with Java snippets, covering audio capture, transcription, and result callbacks, so you can lift those pieces into your own project. For teams weighing offline ASR on Android, this offers a concrete starting point and a model-conversion path rather than just a demo.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category