Downloads · 30 days
0
aoiandroid/distil-whisper-large-v3-litert-int8
distil-whisper-large-v3-litert-int8 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.
📱 Official Engine-Ready INT8 Quantized LiteRT Model Package (.litertlm) for distil-whisper/distil-large-v3
Downloads · 30 days
0
Access
Public
Updated Aug 2, 2026
Repo size
3 GB
Likes
0
Public
Click a slice to open those files.
.litertlm832 MB · 100%
From the Hugging Face model README
📱 Official Engine-Ready INT8 Quantized LiteRT Model Package (.litertlm) for distil-whisper/distil-large-v3
This repository contains the Engine-Compatible LiteRT-LM Binary Container (.litertlm) for distil-whisper/distil-large-v3, compliant with Google CLiteRTLM Engine and TranslateBlue BlueScribe.
LITERTLM Binary Header)| Section Index | Section Type ID | Section Name | Notes |
|---|---|---|---|
| 0 | 5 | LlmMetadataProto | Present (Model architecture: whisper, sample rate: 16000, BPE token specs) |
| 1 | 3 | TFLiteModel | Present (831.52 MB INT8 dynamic quantized model weights) |
| 2 | 6 | HF_Tokenizer_Zlib | Present (Zlib-compressed BPE tokenizer tokenizer.json) |
distil_whisper_large_v3_int8_mobile.litertlm (793.66 MB): Engine-ready binary container with LlmMetadataProto Section 5.LlmMetadataProto Section 5 to prevent bad_optional_access crashes during LiteRTLM.Engine startup.HF_Tokenizer_Zlib (Section 6).