Downloads · 30 days
2
5% of all-time downloads
distil-whisper-large-v3-litert-android
aoiandroid/distil-whisper-large-v3-litert-android
distil-whisper-large-v3-litert-android is a automatic speech recognition model from aoiandroid. Use it when you need speech turned into text. It is set up for litert. The card lists the license as mit.
This repository contains the INT8 quantized LiteRT (TensorFlow Lite) model of distil-whisper/distil-large-v3 optimized for Android on-device ASR execution.
All-time downloads
40
Public
Repo size
832 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.tflite832 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- litert
- License
- mit
- Access
- Public
- Created
- Aug 2, 2026
- Updated
- Aug 2, 2026
- SHA
- 240540cd
Model card
From the Hugging Face model README
Distil-Whisper Large v3 (LiteRT INT8 - Android)
This repository contains the INT8 quantized LiteRT (TensorFlow Lite) model of distil-whisper/distil-large-v3 optimized for Android on-device ASR execution.
Model Summary
- Model Architecture: Distil-Whisper Large v3
- Format: LiteRT Standard ASR Format (
.tflite) - Quantization: INT8
- Target OS: Android 10+ (API 29+)
- Estimated Size: ~832 MB
- Required RAM: >= 2 GB RAM
Usage in Android (Kotlin / Java)
Integrate using LiteRT / TFLite Task API:
val options = ModelOptions.builder()
.setModelPath("distil_whisper_large_v3_int8_mobile.tflite")
.setNumThreads(4)
.build()
Intended Use & Limitations
- Designed for fast on-device English speech recognition on mobile devices.
- Requires phone-class devices with sufficient memory (>= 2GB RAM).
- Task
- Automatic Speech Recognition
- Library
- litert
- License
- mit
- Languages
- en
- Created
- Aug 2, 2026
- Updated
- Aug 2, 2026