v0.5.1
blackboardsh/electrobunv0.5.1Sep 25, 2026by andimarafioti
Upgrading?
AI Summary
The package now defaults to GGML on Apple Silicon, removing the need for manual backend selection and including the Metal runtime in standard installs.
Key Highlights
- CLI selects GGML automatically on Mac without CUDA
- Standard install includes Metal runtime
- Supports macOS 14+ on ARM64 Python
Full Release Notes
## Fixes - The CLI now selects GGML when CUDA is unavailable, so `faster-qwen3-tts custom ...` works on a supported Mac without `--backend ggml`. CUDA hosts still default to the Torch backend; explicit backend selection remains available. - A standard install on native Apple Silicon now includes `qwentts-cpp-python>=0.4.1` and its Metal runtime. Other platforms still use the optional `ggml` extra. Upgrade with `uv pip install -U faster-qwen3-tts`. The Metal wheel supports macOS 14+ on ARM64 Python; Intel Macs and Rosetta Python are outside its supported platforms. ## Changes - [Make Apple Silicon GGML CLI work by default](https://github.com/andimarafioti/faster-qwen3-tts/pull/140) - [Prepare release 0.5.1](https://github.com/andimarafioti/faster-qwen3-tts/pull/141) [Full changelog](https://github.com/andimarafioti/faster-qwen3-tts/compare/v0.5.0...v0.5.1)
Related Repositories
openclaw/openclaw★ 392,706
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
nilbuild/developer-roadmap★ 370,074
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
morluto/rea★ 358,310
Reverse engineer anything with agents, from app behavior down to native binaries.
anomalyco/opencode★ 219,720
The open source coding agent.
n8n-io/n8n★ 208,261
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.