Nemotron streaming on Apple Silicon, safer API token handling, and a lock fix that unblocks Dependabot.
0.2.27 was not published to PyPI. Its publish job expired before approval, so this is the first PyPI release since 0.2.26 and it includes everything in 0.2.27 (local MLX translation, bounded WebSocket sessions, per-session decoder context, the October security refresh and its fixes).
Added
- Nemotron streaming ASR through MLX (
nemotron-mlx-asrextra,--backend nemotron-mlx-asr), using mlx-audio's incremental frontend and cached encoder with the convertedmlx-community/nemotron-3.5-asr-streaming-0.6bcheckpoint. Sessions have independent caches and language prompts; model loading and decoding stay on one dedicated thread. (#426, thanks @clkao)
Fixed
- A non-ASCII API token now gets 401 (REST) or the 4401 close (WebSocket) instead of HTTP 500, and a non-ASCII configured token matches itself. (#479, fixes #478, thanks @goranai)
Maintenance and security
- Rejected requests log the client address (
client=ADDRESS), including REST token failures and refused WebSocket upgrades, so repeated attempts can be traced or fed to fail2ban. The token is never logged. (#476, following discussion #463) - Locked dependencies refreshed for November (Accelerate 1.16.0 in the Voxtral HF graph, Torch 2.11.0 for the
cpuextra on macOS arm64), and the lock now covers only the platforms Torch ships wheels for (Linux x86_64 and aarch64, macOS arm64, Windows AMD64). This fixes the Dependabot update failures. Advisories still held by upstream pins (mostlyqwen-asr==0.0.6, NeMo and Diart) are listed indocs/dependency-audit.md. PyPI installs are unaffected by the lock. (#480) - Reproducible M5 backend evaluation recorded under
benchmarks/evaluations/m5-20261107/. (#444)
New contributors
Full changelog: v0.2.27...v0.2.28