The project (MeloTTS) has been quite since long, newer backends are much
performant and better quality overall.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
We support at this point more extensive backends that are SOTA and
support also voice cloning, and many other features. This backend is
superseded and also poses significant maintenance burden as there is an
open issue https://github.com/mudler/LocalAI/issues/3941 which is still
open as it deps are pinning old versions of grpc.
Closes https://github.com/mudler/LocalAI/issues/3941
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(stores): Actually check a vector is a unit vector/normalized
Instead of just summing the components to see if they equal 1.0, take
the actual magnitude/p-norm of the vector and check that is
approximately 1.0.
Note that this shouldn't change the order of results except in edge
cases if I am too lax with the precision of the equality
comparison. However it should improve performance for normalized
vectors which were being misclassified.
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* fix(stores): Add tests for known results and triangle inequality
This adds some more tests to check the cosine similarity function has
some expected mathematical properties.
Signed-off-by: Richard Palethorpe <io@richiejp.com>
---------
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* chore(stablediffusion-ncn): drop in favor of ggml implementation
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(ci): drop stablediffusion build
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(tests): add
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(tests): try to fixup current tests
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Try to fix tests
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Tests improvements
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(tests): use quality to specify step
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(tests): switch to sd-1.5
also increase prep time for downloading models
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* merge sentencetransformers
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Add alias to silently redirect sentencetransformers to transformers
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Add alias also for transformers-musicgen
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Drop from makefile
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Move tests from sentencetransformers
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Remove sentencetransformers
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Remove tests from CI (part of transformers)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Do not always try to load the tokenizer
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Adapt tests
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Fix typo
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Tiny adjustments
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Add machine tag option, add extraUsage option, grpc-server -> proto -> endpoint extraUsage data is broken for now
Signed-off-by: mintyleaf <mintyleafdev@gmail.com>
* remove redurant timing fields, fix not working timings output
Signed-off-by: mintyleaf <mintyleafdev@gmail.com>
* use middleware for Machine-Tag only if tag is specified
Signed-off-by: mintyleaf <mintyleafdev@gmail.com>
---------
Signed-off-by: mintyleaf <mintyleafdev@gmail.com>
* feat(transformers): merge musicgen functionalities to a single backend
So we optimize space
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* specify type in tests
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Some adaptations for the MusicgenForConditionalGeneration type
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend): add stablediffusion-ggml
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(ci): track stablediffusion-ggml
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fixups
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Use default scheduler and sampler if not specified
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fixups
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Move cfg scale out of diffusers block
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Make it working
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix: set free_params_immediately to false to call the model in sequence
https://github.com/leejet/stable-diffusion.cpp/issues/366
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(bark-cpp): add new bark.cpp backend
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* build on linux only for now
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* track bark.cpp in CI bumps
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Drop old entries from bumper
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* No need to test rwkv specifically, now part of llama.cpp
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backends): Drop bert.cpp
use llama.cpp 3.2 as a drop-in replacement for bert.cpp
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(tests): make test more robust
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(deps): bump llama-cpp to ae8de6d50a09d49545e0afab2e50cc4acfb280e2
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(metal): metal file has moved
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>