🚀 Audiobook Creator v1.3 Release 🎧
This release introduces changes to improve performance and decrease audiobook generation time by utilizing multiple workers of kokoro fastapi and making batched parallel requests for audio generation. This update also adds two env variables whose descriptions have been updated in .env.sample.
To utilize the parallel batch requests during audio generation refer to the updated README where there are instructions for setting up Kokoro with multiple workers and for setting up the env variable for batch parallel requests.
🐳 Docker Image:
You can pull the latest image with (choose cpu/ cuda gpu variant):
docker pull ghcr.io/prakharsr/audiobook_creator_cpu:v1.3docker pull ghcr.io/prakharsr/audiobook_creator_gpu:v1.3For complete instructions on how to run: Goto the Get Started Section
Full Changelog: https://github.com/prakharsr/audiobook-creator/commits/main