---
license: apache-2.0
tags:
  - qhexrt
  - whisper
  - asr
  - hexagon
  - npu
  - qnn
language:
  - en
pipeline_tag: automatic-speech-recognition
---

# whisper-small — QHexRT NPU bundle (Hexagon v79)

Precompiled **Whisper-small** ASR for the **QHexRT** runtime on Qualcomm Hexagon **v79**
(Snapdragon 8 Elite / SM8750, e.g. Galaxy S25). More accurate than
[whisper-base](https://huggingface.co/runanywhere/whisper_base_HNPU) at ~3× the size and ~1.3×
slower decode (still comfortably real-time). Encoder + decoder are Qualcomm AI Hub
`qnn_context_binary` (float/fp16) graphs; the host pipeline is QHexRT's own. Device-validated:
transcription matches the HF `openai/whisper-small` reference exactly.

Measured on S25/v79: 718 ms for 2.67 s of audio (≈3.7× real-time) vs base's 546 ms (≈5×).

## Contents (`v79/`)
| file | what |
|------|------|
| `whisper-small.json` | QHexRT manifest (ASR family, `asr_transcribe` plan; 12 layers, d_model 768) |
| `encoder.bin` | AI Hub Whisper-small encoder (mel → 24 cross-attn KV) |
| `decoder.bin` | AI Hub Whisper-small decoder (greedy step → logits + self-KV) |
| `whisper_mel_filters.bin` | HF 80-mel filter bank `[201,80]` f32 (shared across whisper sizes) |
| `tokenizer.json` | Whisper multilingual tokenizer (vocab 51865, shared) |

## Run (QHexRT CLI)
```bash
huggingface-cli download runanywhere/whisper_small_HNPU --local-dir whisper_small_HNPU
# QNN libs come from the QAIRT SDK (lib/aarch64-android) + the v79 HTP skel; push them next to qhx_asr.
adb push whisper_small_HNPU/v79 /data/local/tmp/wq/whisper_small
adb shell "cd /data/local/tmp/wq && LD_LIBRARY_PATH=. ADSP_LIBRARY_PATH=. \
  ./qhx_asr whisper_small/whisper-small.json libQnnHtp.so libQnnSystem.so whisper_small whisper_small/<audio16k>.wav"
```
Audio: mono WAV (PCM16 or float32); resampled to 16 kHz host-side. Clips ≤ 30 s.

## Notes
- Arch: **v79** only (context binaries are dsp-arch-pinned).
- No custom op-package needed — pure-native AI Hub graphs.
- The QHexRT `asr_transcribe` orchestrator is size-agnostic; base/small/tiny differ only in these bins + manifest dims.
- Source model: `openai/whisper-small`, compiled via Qualcomm AI Hub for `qualcomm-snapdragon-8-elite-for-galaxy`.