v0.5.3
andimarafioti/faster-qwen3-ttsv0.5.3Sep 29, 2026by andimarafioti
Upgrading?
AI Summary
This release makes GGML model loading and synthesis quieter by default in both Python and the CLI by upgrading to qwentts-cpp-python 0.4.2, which includes a native logging filter to hide routine diagnostics while preserving warnings and errors.
Key Highlights
- Quieter GGML loading and synthesis by default
- Native logging filter via qwentts-cpp-python 0.4.2
- Full diagnostics accessible via --verbose or debug log level
- Removed CLI stderr redirection for better error visibility
Full Release Notes
GGML model loading and synthesis are quieter by default in both Python and the CLI. - Require qwentts-cpp-python 0.4.2 and use its native logging filter to hide routine diagnostics while preserving warnings and errors. - Enable full diagnostics with CLI `--verbose` or Python `qwentts_log_level="debug"`. - Remove CLI stderr redirection so download progress and unrelated errors remain visible. - Update installation and logging documentation. Validated with 75 passing tests (15 CUDA-dependent tests skipped) and real synthesis using the released 0.4.2 macOS wheel. Upgrade with `pip install --upgrade faster-qwen3-tts` or `pip install --upgrade "faster-qwen3-tts[ggml]"`.
Related Repositories
public-apis/public-apis★ 491,217
A collective list of free APIs
NousResearch/hermes-agent★ 256,087
The agent that grows with you
yt-dlp/yt-dlp★ 200,261
A feature-rich command-line audio/video downloader
microsoft/markitdown★ 191,560
Python tool for converting files and office documents to Markdown.
Significant-Gravitas/AutoGPT★ 187,699
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.