docs(changelog): note the PyTorch Whisper VRAM budget fix (#2044)

2026-09-10 15:06:52 -07:00
parent 033f8f2f64
commit e501a596d3
1 changed files with 1 additions and 0 deletions
@@ -26,6 +26,7 @@ the frozen-backend fallback mirror it for their toolchains.
 - Stopping a process on macOS no longer fails with "Operation not permitted" when it was already exiting (#2032)
 - A YouTube link blocked by its "not a bot" check now says how to attach signed-in cookies in Dub, instead of quoting yt-dlp's command-line flags (#2036, #2034)
 - An engine that fails to start now says whether it timed out, crashed (with its exit code and last output) or answered wrongly, instead of "did not signal ready: None" (#2037, #2026)
+- PyTorch Whisper runs on 6 GB NVIDIA cards instead of falling back to CPU, because its memory check now fits the model it loads (#2044, #2041)

 ### CI