Downloads · 30 days
25
19% of all-time downloads
sensevoice-rknn
harvestsu/sensevoice-rknn
sensevoice-rknn is a automatic speech recognition model from harvestsu. Use it when you need speech turned into text. It is set up for tensorrt. The card lists the license as other.
Edge-deployment artifacts for SenseVoice-Small offline ASR (encoder + CTC, zh/en/ja/ko/yue), used by OpenVoiceStream on Rockchip NPU (RKNN) and NVIDIA Jetson (TensorRT).
All-time downloads
133
Public
Repo size
4.5 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.rknn2.5 GB · 56%
At a glance
- Task
- Automatic Speech Recognition
- Library
- tensorrt
- License
- other
- Access
- Public
- Created
- Jun 10, 2026
- Updated
- Sep 9, 2026
- SHA
- 671ee310
Model card
From the Hugging Face model README
SenseVoice edge artifacts (RKNN / TensorRT) — for OpenVoiceStream
Edge-deployment artifacts for SenseVoice-Small offline ASR (encoder + CTC, zh/en/ja/ko/yue), used by OpenVoiceStream on Rockchip NPU (RKNN) and NVIDIA Jetson (TensorRT).
Attribution
- Model: SenseVoice-Small by FunAudioLLM (Alibaba / ModelScope) — https://github.com/FunAudioLLM/SenseVoice · https://huggingface.co/FunAudioLLM/SenseVoiceSmall
- Model weights license: FunASR Model Open Source License Agreement — https://github.com/modelscope/FunASR/blob/main/MODEL_LICENSE (redistribution permitted with attribution; retain source/author/model name)
- Source ONNX:
lovemefan/SenseVoice-onnx· sherpa-onnx export bycsukuangfj(k2-fsa). Decode assets (am.mvn,embedding.npy, sentencepiece model) are from the sherpa-onnx SenseVoice export.
The files here are format conversions / derivatives of the above (ONNX → RKNN / activation-rescaled ONNX for TensorRT). They inherit the FunASR Model License; this repo retains attribution per §2.2. No model code from any GPL/AGPL runtime is included — the OpenVoiceStream runtime + converters are independent.
Files
| file | platform | notes |
|---|---|---|
sense-voice-encoder.rk3576.fp16.rknn | RK3576 | fp16 |
sense-voice-encoder.rk3588.fp16-scaled.rknn | RK3588 | fp16 + K=8 activation rescale (fp16-safe on zh) |
sense-voice-encoder.scaled.fixed.onnx | Jetson | rescaled fixed-shape ONNX; engine built on-device with host TensorRT |
sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17.tar.bz2 | RPi / CPU | sherpa-onnx SenseVoice package (model.int8.onnx + tokens) |
am.mvn / embedding.npy / chn_jpn_yue_eng_ko_spectok.bpe.model | RK/Jetson | decode assets |
- Task
- Automatic Speech Recognition
- Library
- tensorrt
- License
- other
- Languages
- zh, en, ja, ko, yue
- Created
- Jun 10, 2026
- Updated
- Sep 9, 2026