v0.5.1

facebookresearch/sam-audiov0.5.1Sep 25, 2026by andimarafioti

Upgrading?

AI Summary

The CLI now automatically selects the GGML backend on Apple Silicon Macs when CUDA is unavailable, and standard installs now include the Metal runtime.

Key Highlights

  • GGML CLI works by default on supported Mac
  • Standard install includes Metal runtime on Apple Silicon
  • CUDA hosts still default to Torch backend
  • Explicit backend selection remains available

New Features

  • Automatic backend selection on Mac
  • Inclusion of Metal runtime in standard install

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