Plokštės rinkinys SaraKIT Raspberry Pi CM4

Trumpai apie prekę

Prekė: Plokštės rinkinys SaraKIT Raspberry Pi CM4. Kategorija: Priedai.

• Gamintojas: no brand
• Modelis: SARAKIT-V-01 without accesories

SaraKIT is an expansion board for the Raspberry Pi CM4. It is equipped with 3 microphones with sound location function and stereo output for artificial intelligence and voice projects. Two independent BLDC controllers allow for quiet and precise motor control in device designs. It is equipped with a CSI interface with two cameras and two accelerometers, a gyroscope and a temperature sensor.

Create modern, powerful, and flexible voice products with the Raspberry Pi, integrated with Amazon Alexa, Google Assistant, ChatGPT, etc.

Create voice-controlled robots. Communicate with home, office, or other devices in everyday life, all with your voice.

Application

• Smart Speaker
• Intelligent voice assistant systems
• Voice Recorders
• Voice conferencing system
• Meeting with communication equipment
• Voice Interactive Robot
• Car Voice Assistant
• Other scenarios require voice commands
• Other scenarios requiring quiet and precise motors

Speech recognition with SaraKIT

SaraKIT is equipped with three microphones and a specialized sound processor that clears voice and supports speech recognition on the Raspberry Pi, offering a significant step in sharing offline voice command functionality, independent of the cloud. While many speech recognition tools are available online, and cloud-based data analytics tools like Google Speech to Text are among the best and most efficient, as discussed in my other guide, this article focuses on offline speech recognition — without the need for an internet connection.

In search of the best and easiest tool to configure, I came across a noteworthy solution, currently recommended for offline speech recognition - Vosk API:

Vosk speech recognition toolkit

Vosk is an offline open source speech recognition toolkit that makes it easy to recognize speech in more than 20 languages and dialects, including English, German, French, Spanish, and more. Its models are compact (about 50 Mb), but support continuous transcription of large vocabulary, offer lag-free response through the streaming API, offer reconfigurable vocabulary, and identify speakers. Vosk supports a range of applications, from chatbots and smart home devices to virtual assistants and subtitle creation, scaling from small devices like Raspberry Pi or Android smartphones to large clusters.

Vosk homepage: https://alphacephei.com/vosk/

GitHub Vosk: https://github.com/alphacep/vosk-api

Installation on SaraKIT:

Assuming that the basic SaraKIT drivers are already installed https://sarakit.saraai.com/getting-started/software , follow these steps to install:

sudo apt-get install pip sudo apt-get install -y python3-pyaudio sudo pip3 install vosk git clone https://github.com/SaraEye/SaraKIT-Speech-Recognition-Vosk-Raspberry-Pi SpeechRecognition cd SpeechRecognition

To use a language other than English, download the required language model from https://alphacephei.com/vosk/models and place it in the “models” directory.

Start speech recognition by running:

python SpeechRecognition.py

Below is a script for speech recognition in the language of your choice, available at

https://github.com/SaraEye/SaraKIT-Speech-Recognition-Vosk-Raspberry-Pi :

It may happen that you use all the power of the Raspberry Pi, for example, to analyze the image, and then you may find that you lack the computing power to recognize speech. In such cases, you will need to use cloud analytics on a more powerful computer. You can set up your own server and still use Vosk, or you can opt for other tools like Google Speech to Text.

Text to Speech with SaraKIT

SaraKIT is equipped with three microphones and a specialized sound processor that clears the sound of voice and supports speech recognition on the Raspberry Pi from a distance of up to 5 meters, as described in our “Speech Recognition” section. However, to complete the setup, we are now paying attention to text-to-speech (TTS) processing, which can be extremely useful when creating voice assistants, speaking devices or integration with home automation (HA) systems. Although the best TTS systems currently available are online services such as ElevenLabs (paid) that offer the highest voice quality, or Google Text to Speech (details in a separate section), here we focus on offline text-to-speech processing.

After searching the internet for the best, quick and easy to install offline option, Piper stands out as the best choice (if you find something better, let us know).

Piper is fast, generates high-quality voice in real time and is optimized for the Raspberry Pi 4. Although its installation is simple, I have further simplified it for you, and you will find a demonstration with a description below.

You can test Piper at:

https://rhasspy.github.io/piper-samples/

Piper on GitHub:

https://github.com/rhasspy/piper

https://github.com/rhasspy/piper-phonemize (additional component)

Voices for Piper:

https://huggingface.co/rhasspy/piper-voices/tree/main

GitHub:

https://github.com/SaraEye (C++, Python examples)

YouTube SaraKIT Playlist:

https://www.youtube.com/playlist?list=PLOJbQ7GTI25qS3W62p32KOe1jh8DDpwMb

Specifications