mempool/umbrel-apps
mempool/umbrel-apps
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update kokoro to v0.2.4-master (#4292)

Browse Source
This commit is contained in:
Alexander L. 2025-12-18 22:15:58 +01:00 committed by GitHub
parent 1f09e75bc0
commit f6899330d2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 10 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
kokoro/docker-compose.yml
View File

@ -7,6 +7,6 @@ services:
APP_PORT: 8880
web:
image: ghcr.io/remsky/kokoro-fastapi-cpu:v0.2.4@sha256:c8812546d358cbfd6a5c4087a28795b2b001d8e32d7a322eedd246e6bc13cb55
image: ghcr.io/remsky/kokoro-fastapi-cpu:v0.2.4-master@sha256:03a5201c0327f1f1a1619ebbd9722e3b5477b0cccc588aaddb74dd89aad67f15
user: "1000:1000"
restart: on-failure

23
kokoro/umbrel-app.yml
View File

@ -3,7 +3,7 @@ id: kokoro
name: Kokoro
tagline: An intelligent, high-quality TTS solution
category: ai
version: "0.2.4"
version: "0.2.4-master"
port: 8877
description: >-
Kokoro is an advanced Text-to-Speech (TTS) model that delivers impressive speech quality with only 82 million parameters, making it competitive with much larger and more resource-intensive models. Despite its relatively compact architecture, Kokoro effectively transforms text into clear, natural-sounding speech, making it an excellent choice for applications relying on speech synthesis. The model has been specifically designed to ensure high efficiency and fast processing, making it suitable for both resource-constrained environments and production systems. In comparison to traditional TTS models, which often require substantial computational resources, Kokoro offers a more cost-effective and faster alternative without compromising the quality of speech output.
@ -27,21 +27,16 @@ gallery:
- 2.jpg
- 3.jpg
releaseNotes: >-
This release includes numerous improvements and fixes:
This release includes improvements and fixes:
- Fixed custom phenomes and made them more robust
- Updated PyTorch for RTX 50 Series GPU support
- Reduced Docker image size
- Added configurable logging level with environment variable support
- Improved build stability and compatibility
- Enhanced build times through parallelization
- Added support for Apple Silicon with MPS acceleration
- Improved text normalization and parsing capabilities
- Enhanced audio quality and pause handling
- Added Chinese punctuation-based sentence splitting
- Fixed segmentation faults and various stability issues
- Added volume multiplier setting
- Improved streaming and download functionality
- Better safety checks for captioned speech
- Fixed phenome handling and normalization issues
Full release notes are available at https://github.com/remsky/Kokoro-FastAPI/releases/tag/v0.2.4
Full release notes are available at https://github.com/remsky/Kokoro-FastAPI/releases/tag/v0.2.4-master
dependencies: []
path: "/web"
defaultUsername: ""