talk.wasm : add audio pre-processing + bump memory

This commit is contained in:
Georgi Gerganov
2022-11-24 00:34:00 +02:00
parent be3b720f96
commit 37422ed733
4 changed files with 11 additions and 5 deletions

View File

@ -34,7 +34,7 @@ In order to run this demo efficiently, you need to have the following:
- Latest Chrome or Firefox browser (Safari is not supported)
- Run this on a desktop or laptop with modern CPU (a mobile phone will likely not be good enough)
- Speak phrases that are no longer than 10 seconds - this is the audio context of the AI
- The web-page uses about 1.4GB of RAM
- The web-page uses about 1.6GB of RAM
Notice that this demo is using the smallest GPT-2 model, so the generated text responses are not always very good.
Also, the prompting strategy can likely be improved to achieve better results.