Bruce, all,
I have also been looking at the board, especially for the neural-network
component.
Is there any model on how AI or neural-networks can be used for voice
(codec2) encoding or decoding?
73
kristoff - ON1ARF
On 16/02/19 05:14, Bruce Perens wrote:
Take a look at this as a platform for hosting Codec2: $20 module
contains a generic RISC-V CPU, neural network hardware, hardware FFT
(both on the audio module and a stand-alone one), audio processor,
WiFi,
https://www.seeedstudio.com/Sipeed-M1w-dock-suit-M1w-dock-2-4-inch-LCD-OV2640-K210-Dev-Board-1st-RV64-AI-board-for-Edge-Computing-p-3207.html
The CPU data sheet is here:
https://s3.cn-north-1.amazonaws.com.cn/dl.kendryte.com/documents/kendryte_datasheet_20181011163248_en.pdf
I ordered a couple to see if I could host Codec2 and softmodems on
them, but they have potential to do more than that. The $9 module
without the board is already sold out, they still have the $20 board
version as I write this.
Thanks
Bruce
_______________________________________________
Freetel-codec2 mailing list
Freetel-codec2@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/freetel-codec2
_______________________________________________
Freetel-codec2 mailing list
Freetel-codec2@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/freetel-codec2
