4 Commits

Include renames

Author	SHA1	Message	Date
xavierk	25c5132b03	docs(models): mark ladder thresholds provisional until ticket 19 is recorded ... The rung cutoffs cite ticket 19's transcribe peaks, but ticket 19 is still open and its measurement is not in this repository. The code and test docstrings now say the numbers are provisional calibration to replace, rather than evidence. Also formats the niri guard tests to the project line length.	2026-11-06 18:29:15 +05:30
xavierk	7978ba7d76	fix(models): recommend the ladder rung from the installed build and free memory ... get_recommended_model() now keys to the backend the installed whisper.cpp build actually has (detect_pywhispercpp_gpu_backend) and to free memory measured at recommendation time: free VRAM on a discrete GPU for a Vulkan or CUDA build, free system RAM otherwise. The result is a rung of the model ladder, so a Vulkan-capable Nvidia card reaches the ladder instead of the total-memory tiers, and unquantized turbo, the large family and medium are never a default. Manual selections are untouched. The informational hardware probe no longer decides the model. Dead VRAM-total parsing is removed. free_memory_for_backend() holds the source choice; the floor-rung map is shared by rung selection and step-down.	2026-11-06 18:25:17 +05:30
soubarnak	987d8eec29	fix(models): use ticket 19 measured peaks for ladder thresholds ... q8_0 threshold becomes 1644 MiB (1132+512) and q5_0 becomes 1358 MiB (846+512) per the recorded baseline recommendation, replacing the on-disk-size proxies. Tests pin the measured values and the 1644/1358 boundaries.	2026-11-06 09:00:47 +05:30
soubarnak	df771d8fb1	feat(models): memory-aware whisper.cpp ladder with conditional backend order ... Free memory picks the load-time rung (large-v3-turbo-q8_0 default, q5_0 under 1086 MiB free, small/small.en floor) for unpinned default configs; thresholds derive from catalog sizes plus the protocol's 512 MiB headroom. A manual pin is never overridden, and a failed load steps one rung down and retries exactly once before surfacing. CUDA ranks before Vulkan only with a complete architecture-matching toolkit (nvidia-smi GPU, nvcc, compute capability >= 7.0); otherwise Vulkan, then CPU. The driver-only CUDA recommendation now demotes to CPU logic instead of naming an unreachable VRAM ladder. Refs #20	2026-11-06 01:48:20 +05:30