Open YikeDecodaAI opened 1 year ago
Hello YikeDecodaAI, the project already includes the complete source code. The corresponding image is built using GitHub Action from the Dockerfile in the project root directory. Therefore, you only need to execute docker build -t namespace/faster-sadtalker-api:0.1.3 .
to build the same image I provided.
Another thing to note is that if you want to use other TTS systems, you need to maintain consistency with the TTS interface. You can check the interactive documentation at localhost:9566/docs
after launching the TTS server.
Wish you smooth progress, and please keep in touch if there are any issues.
The image you used in docker-compose.yml was pulled. Can you provide the source code of these two images, paidax/faster-sadtalker-api:0.1.3 and paidax/tts_modelscope:0.1.3? I would like to modify them. Change tts to bark model, and pass in pictures and audio like sadtalker