Artificial intelligence


What types of cameras are supported on AI image recognition products?

With ESP32 as its main control chip, ESP-EYE supports various types of cameras, such as 0V2640, OV3660, OV5640, OV7725, etc. Please see esp32-camera Github.

Which versions of ESP-IDF are supported by ESP-WHO?

The subsequent supported versions will be updated on ESP-WHO Github.

Is there any information about the WeChat mini program of ESP-EYE?

For open source resources of ESP-EYE mini program demo, please check EspEyeForWeChat.

What languages are supported by the esp-skainet demo?

Only Chinese and English currently.

What model frameworks does ESP-DL support?

Currently, ESP-DL supports models from mxnet, pytorch, and tensorflow.

Does ESP-DL support all models of the three platforms mentioned above (mxnet, pytorch, and tensorflow)?

ESP-DL supports models in which all the operators are supported by ESP-DL. Please check layer for the supported operators.

Can the model files of ESP-SKAINET be stored in the SD card?


How to customize command words in ESP-SKAINET?

For custom command words, please refer to the Custom Command Word Method.

How to reduce the system footprint of AI speech models?

You can choose to turn off the three functions, namely AEC, AE, and VAD.

What is the difference between a 16-bit quantization model and an 8-bit quantization model?

The 16-bit quantization model has higher precision and more accurate results, while the 8-bit quantization model is more lightweight.

How does the AI voice model modify the number of microphone channels?

The number of microphone channels and the number of playback channels can be configured in the AFE.

How do I get the actual audio captured in the development board?

To obtain the actual audio, an SD card interface is required to store the audio files to the SD card.

Do you have relevant study materials for ESP-SR GitHub?

Please refer to ESP-SR User Guide.

Do you have relevant study materials for ESP-DL?

How does ESP32-S3 customize English command words for recognition?

  • For MultiNet6, you need to prepare commands_en.txt to customize English command words. For MultiNet5, you need to use the script to convert English command words into phonemes that can be recognized by multinet. For details, please refer to esp-sr/tool.