feat(tts): Add Kokoro backend (#4616)

* feat(kokoro): Add new TTS backend

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add kokoro to images

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Support combined voices

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Ignore pt and onnx

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add plbert and istfnet

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-01-16 22:23:09 +01:00 committed by GitHub
parent de4aa9fb1d
commit acb2eb23c8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
19 changed files with 1303 additions and 3 deletions

View file

@ -15,7 +15,7 @@ ARG TARGETARCH
ARG TARGETVARIANT
ENV DEBIAN_FRONTEND=noninteractive
ENV EXTERNAL_GRPC_BACKENDS="coqui:/build/backend/python/coqui/run.sh,huggingface-embeddings:/build/backend/python/sentencetransformers/run.sh,transformers:/build/backend/python/transformers/run.sh,sentencetransformers:/build/backend/python/sentencetransformers/run.sh,rerankers:/build/backend/python/rerankers/run.sh,autogptq:/build/backend/python/autogptq/run.sh,bark:/build/backend/python/bark/run.sh,diffusers:/build/backend/python/diffusers/run.sh,openvoice:/build/backend/python/openvoice/run.sh,vall-e-x:/build/backend/python/vall-e-x/run.sh,vllm:/build/backend/python/vllm/run.sh,mamba:/build/backend/python/mamba/run.sh,exllama2:/build/backend/python/exllama2/run.sh,transformers-musicgen:/build/backend/python/transformers-musicgen/run.sh,parler-tts:/build/backend/python/parler-tts/run.sh"
ENV EXTERNAL_GRPC_BACKENDS="coqui:/build/backend/python/coqui/run.sh,huggingface-embeddings:/build/backend/python/sentencetransformers/run.sh,transformers:/build/backend/python/transformers/run.sh,sentencetransformers:/build/backend/python/sentencetransformers/run.sh,rerankers:/build/backend/python/rerankers/run.sh,autogptq:/build/backend/python/autogptq/run.sh,bark:/build/backend/python/bark/run.sh,diffusers:/build/backend/python/diffusers/run.sh,openvoice:/build/backend/python/openvoice/run.sh,kokoro:/build/backend/python/kokoro/run.sh,vall-e-x:/build/backend/python/vall-e-x/run.sh,vllm:/build/backend/python/vllm/run.sh,mamba:/build/backend/python/mamba/run.sh,exllama2:/build/backend/python/exllama2/run.sh,transformers-musicgen:/build/backend/python/transformers-musicgen/run.sh,parler-tts:/build/backend/python/parler-tts/run.sh"
RUN apt-get update && \
@ -436,6 +436,10 @@ SHELL ["/bin/bash", "-c"]
# Splitting the backends into more groups with fewer items results in a larger image, but a smaller size for the largest layer
# Splitting the backends into fewer groups with more items results in a smaller image, but a larger size for the largest layer
RUN if [[ ( "${IMAGE_TYPE}" == "extras ")]]; then \
apt-get -qq -y install espeak-ng \
; fi
RUN if [[ ( "${EXTRA_BACKENDS}" =~ "coqui" || -z "${EXTRA_BACKENDS}" ) && "$IMAGE_TYPE" == "extras" ]]; then \
make -C backend/python/coqui \
; fi && \
@ -452,6 +456,9 @@ RUN if [[ ( "${EXTRA_BACKENDS}" =~ "coqui" || -z "${EXTRA_BACKENDS}" ) && "$IMAG
RUN if [[ ( "${EXTRA_BACKENDS}" =~ "vall-e-x" || -z "${EXTRA_BACKENDS}" ) && "$IMAGE_TYPE" == "extras" ]]; then \
make -C backend/python/vall-e-x \
; fi && \
if [[ ( "${EXTRA_BACKENDS}" =~ "kokoro" || -z "${EXTRA_BACKENDS}" ) && "$IMAGE_TYPE" == "extras" ]]; then \
make -C backend/python/kokoro \
; fi && \
if [[ ( "${EXTRA_BACKENDS}" =~ "openvoice" || -z "${EXTRA_BACKENDS}" ) && "$IMAGE_TYPE" == "extras" ]]; then \
make -C backend/python/openvoice \
; fi && \