---
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 + v81)

Precompiled **Whisper-small** ASR (12 layers, d_model 768) for the **QHexRT** runtime on the Qualcomm Hexagon
NPU. Two arch-pinned bundles ship as sibling dirs:

| dir | Hexagon arch | device | encoder path | device-validated |
|-----|--------------|--------|--------------|------------------|
| `v79/` | v79 (SM8750, Galaxy S25) | Snapdragon 8 Elite | AI-Hub **in-graph** conv | ✅ transcript == HF |
| `v81/` | v81 (SM8850, soc 87) | Snapdragon 8 Elite Gen 5 | **forge host-conv** (`encoder_features`) | ✅ **WER 0** |

A context binary won't load on another arch (`soc_model` + `dsp_arch` baked in). The same `qhx_asr` runs both
bundles (it branches on the encoder input). The `asr_transcribe` orchestrator is size-agnostic — base/small
differ only in these bins + the manifest dims.

---

## `v81/` — Hexagon v81 (SM8850), compiled with **forge** (QAIRT 2.47)

Same host-conv decomposition as whisper-base (the HTP-hostile conv stem runs host-side from
`whisper_conv_stem.bin`; the encoder graph starts at post-conv `encoder_features [1500,768]`). fp16 encoder +
decoder. This bundle is a **new forge port** — the spec (`recipes/whisper-small`) is generated from the same
exporter that produced the validated whisper-base v81, then device-gated on hardware.

### Files (`v81/`)
| file | role |
|------|------|
| `whisper-small.json` | QHexRT manifest (`asr_transcribe` plan; 12 layers / d768 / 12 heads) |
| `whispersmall_enc_f16.bin` | encoder (post-conv `encoder_features` → per-layer cross-attn K/V) |
| `whispersmall_dec_f16.bin` | autoregressive decoder (self+cross attn, in-graph int32 embed + tied lm-head) |
| `whisper_conv_stem.bin` | host-side conv-stem weights `[c1w,c1b,c2w,c2b,pos]` |
| `whisper_small_mel_filters.bin` | HF 80-mel filter bank (host log-mel) |
| `tokenizer.json` | Whisper tokenizer (vocab 51865) |

### Run (`v81/`)
```bash
huggingface-cli download runanywhere/whisper_small_HNPU --local-dir whisper_small_HNPU
adb push whisper_small_HNPU/v81 /data/local/tmp/wq/whisper_small   # QNN libs + v81 HTP skel from the QAIRT SDK
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"
```

### Measured (SM8850 / v81, soc 87, QAIRT 2.47)
- **WER = 0** vs HF `openai/whisper-small` on a clean LibriSpeech clip *and* a 23 s clip (decode runs the full
  length). Encoder cross-KV cosine **1.00000**, decoder 12/12 teacher-forced + greedy chain MATCH (export gate).

---

## `v79/` — Hexagon v79 (SM8750, Galaxy S25), Qualcomm AI Hub graphs

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).

### Files (`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) |

Audio: mono WAV (PCM16 or float32); resampled to 16 kHz host-side. Clips ≤ 30 s. No custom op-package needed.
Source model: `openai/whisper-small`.

_v81 bundle built + device-validated with [QHexRT](https://github.com/RunanywhereAI/QHexRT) `forge` — `recipes/whisper-small`._