Product Guide
Linux PC
AI Accelerator Card
LLM-8850 Card
Large Language Models
LLM
Real-Time AI Voice Assistant
XiaoZhi Voice Assistant
AtomS3R-M12 Volcengine Kit
Offline Voice Recognition
Industrial Control
IoT Measuring Instruments
Air Quality
Module13.2 PPS
VAMeter
T-Lite
Ezdata
Ethernet Camera
PoECAM
Wi-Fi Camera
Unit CamS3/-5MP
AI Camera
LoRa & LoRaWAN
Motor Control
Restore Factory Firmware
DIP Switch Usage Guide
Module GPS v2.0
Module GNSS
Module ExtPort For Core2
Module LoRa868 V1.2
SenseVoice
SenseVoice is a speech recognition and understanding model that can efficiently and accurately convert spoken content into text, supporting multilingual and multi-scenario speech processing.
- Manually download the model and upload it to raspberrypi5, or pull the model repository using the following command.
Note
If git lfs is not installed, please refer to git lfs installation instructions for installation.
git clone https://huggingface.co/AXERA-TECH/SenseVoiceFile Description:
m5stack@raspberrypi:~/rsp/SenseVoice $ ls -lh
total 464K
-rw-rw-r-- 1 m5stack m5stack 11K Aug 12 16:38 am.mvn
-rw-rw-r-- 1 m5stack m5stack 369K Aug 12 16:38 chn_jpn_yue_eng_ko_spectok.bpe.model
-rw-rw-r-- 1 m5stack m5stack 0 Aug 12 16:38 config.json
-rw-rw-r-- 1 m5stack m5stack 108 Aug 12 16:38 download_dataset.sh
-rw-rw-r-- 1 m5stack m5stack 893 Aug 12 16:38 download_utils.py
drwxrwxr-x 2 m5stack m5stack 4.0K Aug 12 16:38 embeddings
-rw-rw-r-- 1 m5stack m5stack 17K Aug 12 16:38 frontend.py
-rw-rw-r-- 1 m5stack m5stack 1.1K Aug 12 16:38 LICENSE
-rw-rw-r-- 1 m5stack m5stack 1.6K Aug 12 16:38 main.py
-rw-rw-r-- 1 m5stack m5stack 3.2K Aug 12 16:38 print_utils.py
-rw-rw-r-- 1 m5stack m5stack 1.5K Aug 12 16:38 README.md
-rw-rw-r-- 1 m5stack m5stack 71 Aug 12 16:38 requirements.txt
drwxrwxr-x 2 m5stack m5stack 4.0K Aug 12 16:38 sensevoice_ax650
-rw-rw-r-- 1 m5stack m5stack 9.1K Aug 12 16:38 SenseVoiceAx.py
-rw-rw-r-- 1 m5stack m5stack 2.5K Aug 12 16:38 test_wer.py
-rw-rw-r-- 1 m5stack m5stack 4.7K Aug 12 16:38 tokenizer.py- Create a virtual environment
python -m venv sensevoice- Activate the virtual environment
source sensevoice/bin/activate- Install dependencies
pip install https://github.com/AXERA-TECH/pyaxengine/releases/download/0.1.3.rc1/axengine-0.1.3-py3-none-any.whl
pip install -r requirements.txt- Run
python main.py -i test.mp3| Parameter Name | Description | Default |
|---|---|---|
| --input/-i | Input audio file | - |
| --language/-l | Recognition language, supports auto, zh, en, yue, ja, ko | auto |
Note
The model will be automatically downloaded on the first run.
Execution result example:
(sensevoice) m5stack@raspberrypi:~/rsp/SenseVoice $ python main.py -i test_en.mp3
[INFO] Available providers: ['AXCLRTExecutionProvider']
input_audio: test_en.mp3
language: auto
use_itn: True
model_path: /home/m5stack/rsp/SenseVoice/models/SenseVoice/sensevoice_ax650/sensevoice.axmodel
[INFO] Using provider: AXCLRTExecutionProvider
[INFO] SOC Name: AX650N
[INFO] VNPU type: VNPUType.DISABLED
[INFO] Compiler version: 4.0 156de6f7
RTF: 0.015400904924311537 Latency: 0.463259220123291s Total length: 30.08s
['You want to be a nurse or an archi', "A lawyer or a member of our military. you''re going to need a", 'Eduducation for every single one of those caree', 'Not drop out of school and just drop into a good j', "You''ve got to train for it", "And learn for it. And this isn't just impo", 'lifeIn your own future. what you make', 'Will decide nothing less than the future of this country..']