diff options
| author | 2026-05-13 13:43:23 +0100 | |
|---|---|---|
| committer | 2026-05-13 13:43:23 +0100 | |
| commit | 0806967e099b8ac6132a93271ad0c19b336775b6 (patch) | |
| tree | 9aac58b4d246919396fa0a4b8f6e17a918d0ae83 | |
| parent | d643aaf8a3a3fc8a31f39cb2ae3eaaf681300d4e (diff) | |
| download | dotfiles-0806967e099b8ac6132a93271ad0c19b336775b6.tar.gz dotfiles-0806967e099b8ac6132a93271ad0c19b336775b6.tar.bz2 dotfiles-0806967e099b8ac6132a93271ad0c19b336775b6.zip | |
chore(pkg): switch whisper.cpp -> whisper.cpp-vulkan
Drops the libggml-git transitive dependency in favor of llama.cpp-vulkan
(versioned release). Vulkan acceleration on UHD 620 is unlikely to help
with the base model, but this gets us off a rolling -git package.
| -rw-r--r-- | meta/extra.txt | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/meta/extra.txt b/meta/extra.txt index 36c311f..0183ad1 100644 --- a/meta/extra.txt +++ b/meta/extra.txt @@ -12,5 +12,5 @@ tesseract-data-por # Speech-to-text (used by ~/.local/bin/dictate) # `base` multilingual: ~142 MB, ~7-10x realtime on a 4c CPU. Override # WHISPER_MODEL in the script's environment to use a different ggml model. -whisper.cpp +whisper.cpp-vulkan whisper.cpp-model-base |
