Downloads · 30 days
0
qualcomm-ai-hub-community/phowhisper-small-vi-snapdragon-8gen3-qnn-int8
phowhisper-small-vi-snapdragon-8gen3-qnn-int8 is a automatic speech recognition model from qualcomm-ai-hub-community. Use it when you need speech turned into text. The card lists the license as bsd-3-clause.
PhoWhisper-small (VinAI, BSD-3-Clause) is the strongest open Vietnamese speech recognizer — 6.33% WER on VIVOS and 11.08% on CommonVoice-vi (paper), roughly half the error rate of stock Whisper-small on Vietnamese. No…
Downloads · 30 days
0
Access
Public
Updated Aug 2, 2026
Repo size
292 MB
Likes
0
Public
Click a slice to open those files.
.bin292 MB · 100%
From the Hugging Face model README
PhoWhisper-small (VinAI, BSD-3-Clause) is the strongest open Vietnamese speech recognizer — 6.33% WER on VIVOS and 11.08% on CommonVoice-vi (paper), roughly half the error rate of stock Whisper-small on Vietnamese. No compiled Snapdragon-NPU build of it was published anywhere as of this upload; this package provides one for Snapdragon 8 Gen 3 phones.
| Component | Inference | Peak memory | Profile job |
|---|---|---|---|
| Encoder (30 s window) | 26.4 ms | 133.6 MB | jpey22z15 |
| Decoder (per token) | 6.2 ms | 169.7 MB | j5w4xxl6g |
≈ 150 ms for a typical 20-token Vietnamese utterance — far faster than real-time on a mid-range 2024 flagship chip.
--quantize_full_type int8 --quantize_io, applied server-side at compile — no local AIMET needed) compiles and runs fast for both components.import qai_hub as hub
from qai_hub_models.models._shared.hf_whisper.model import HfWhisperEncoder, HfWhisperDecoder
device = hub.Device(attributes="chipset:qualcomm-snapdragon-8gen3")
for name, cls in (("encoder", HfWhisperEncoder), ("decoder", HfWhisperDecoder)):
component = cls.from_pretrained(hf_whisper_version="vinai/PhoWhisper-small").eval()
spec = component.get_input_spec()
hub.submit_compile_job(
model=component.convert_to_torchscript(spec), device=device, input_specs=spec,
options="--target_runtime qnn_context_binary --quantize_full_type int8 --quantize_io",
name=f"phowhisper-small-{name}-int8")
Requires Python ≥ 3.10, pip install "qai-hub-models[whisper-small]", and an aihub.qualcomm.com API token. I/O is quantized per --quantize_io; exact tensor specs are on the job pages. Companion QCS6490/IoT builds of Whisper-base/small live in this org; the same recipe with the QCS6490 target produces a PhoWhisper build for Dragonwing boards.
Base model: vinai/PhoWhisper-small (BSD-3-Clause) — please cite the PhoWhisper paper. Export wrappers: qualcomm/ai-hub-models (BSD-3-Clause); related community validation: PR #322. Prepared by Phạm Văn Ngoan. Not an official Qualcomm or VinAI release; community-contributed, moderated for structure only.