Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: ProjectEGU/whisper-for-low-vram Loading
base: main
Choose a base ref
...
head repository: pessimal/whisper-for-low-vram Loading
compare: main
Choose a head ref
Checking mergeability… Don’t worry, you can still create the pull request.
  • 9 commits
  • 10 files changed
  • 8 contributors

Commits on Oct 4, 2022

  1. alternate loading of encoder and decoder to enable running large mode… 

    …l with 8GB VRAM
    ProjectEGU authored and ProjectEGU committed Oct 4, 2022
    Configuration menu
    Copy the full SHA
    9984f21 View commit details
    Browse the repository at this point in the history

  2. update README.md with install command

    ProjectEGU authored and ProjectEGU committed Oct 4, 2022
    Configuration menu
    Copy the full SHA
    64a9d16 View commit details
    Browse the repository at this point in the history

  3. ensure unloading of model from GPU by moving it to CPU; update instal… 

    …l command in README.md
    ProjectEGU authored and ProjectEGU committed Oct 4, 2022
    Configuration menu
    Copy the full SHA
    fb5a003 View commit details
    Browse the repository at this point in the history

Commits on Oct 25, 2022

  1. Add --threads option to transcribe (openai#278) 

    * Add --threads option to transcribe

Torch on CPU uses by default number_of_cores/2. This option allows to
override this default.

* Update transcribe.py

Co-authored-by: Jong Wook Kim <[email protected]>
    @eudoxos @jongwook @pessimal
    2 people authored and pessimal committed Oct 25, 2022
    Configuration menu
    Copy the full SHA
    a7e5ffa View commit details
    Browse the repository at this point in the history

  2. infer download_root from XDG_CACHE_HOME if avail (openai#257)

    @dmarx @pessimal
    dmarx authored and pessimal committed Oct 25, 2022
    Configuration menu
    Copy the full SHA
    64ca030 View commit details
    Browse the repository at this point in the history

  3. transcribe() on English-only model won't complain when language="en" … 

    …is not given
    @jongwook @pessimal
    jongwook authored and pessimal committed Oct 25, 2022
    Configuration menu
    Copy the full SHA
    96e12ae View commit details
    Browse the repository at this point in the history

  4. Fix bug (openai#305) 

    Fix bug: RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument index in method wrapper__index_select)
    @MichaelMonashev @pessimal
    MichaelMonashev authored and pessimal committed Oct 25, 2022
    Configuration menu
    Copy the full SHA
    f26829c View commit details
    Browse the repository at this point in the history

  5. Add package metadata to setup.py (openai#315) 

    Add project summary, license, etc. for display with
"pip show" and similar Python package distribution tools.
    @brainwane @pessimal
    brainwane authored and pessimal committed Oct 25, 2022
    Configuration menu
    Copy the full SHA
    a0de10a View commit details
    Browse the repository at this point in the history

  6. Fix attention caching to make it actually work (openai#370)

    @vickianand @pessimal
    vickianand authored and pessimal committed Oct 25, 2022
    Configuration menu
    Copy the full SHA
    75455f9 View commit details
    Browse the repository at this point in the history
Loading