UniqAI/openedai-speech
1
0
Fork 0
mirror of https://github.com/matatonic/openedai-speech synced 2025-06-26 18:16:32 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

0.17.3 - fix 44khz piper voices like fr_FR-tom-medium

Browse Source
This commit is contained in:
matatonic 2024-08-15 16:09:35 -04:00
parent 20871dbcfb
commit b5d0dafd7d
4 changed files with 36 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
Dockerfile
View File

@ -3,16 +3,25 @@ FROM python:3.11-slim
RUN --mount=type=cache,target=/root/.cache/pip pip install -U pip
ARG TARGETPLATFORM
RUN apt-get update && apt-get install --no-install-recommends -y curl ffmpeg
RUN if [ "$TARGETPLATFORM" != "linux/amd64" ]; then apt-get install --no-install-recommends -y build-essential ; fi
RUN if [ "$TARGETPLATFORM" != "linux/amd64" ]; then curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y ; fi
ENV PATH="/root/.cargo/bin:${PATH}"
# for deepspeed support - doesn't seem worth it, image +7.5GB, over the 10GB ghcr.io limit, and no noticable gain in speed or VRAM usage?
#RUN curl -O https://developer.download.nvidia.com/compute/cuda/repos/debian11/x86_64/cuda-keyring_1.1-1_all.deb
#RUN dpkg -i cuda-keyring_1.1-1_all.deb && rm cuda-keyring_1.1-1_all.deb
#RUN apt-get update && apt-get install --no-install-recommends -y libaio-dev build-essential cuda-toolkit
RUN <<EOF
apt-get update
apt-get install --no-install-recommends -y curl ffmpeg
if [ "$TARGETPLATFORM" != "linux/amd64" ]; then
apt-get install --no-install-recommends -y build-essential
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
fi
# for deepspeed support - image +7.5GB, over the 10GB ghcr.io limit, and no noticable gain in speed or VRAM usage?
#curl -O https://developer.download.nvidia.com/compute/cuda/repos/debian11/x86_64/cuda-keyring_1.1-1_all.deb
#dpkg -i cuda-keyring_1.1-1_all.deb
#rm cuda-keyring_1.1-1_all.deb
#apt-get install --no-install-recommends -y libaio-dev build-essential cuda-toolkit
apt-get clean
rm -rf /var/lib/apt/lists/*
EOF
#ENV CUDA_HOME=/usr/local/cuda
RUN apt-get clean && rm -rf /var/lib/apt/lists/*
ENV PATH="/root/.cargo/bin:${PATH}"
WORKDIR /app
RUN mkdir -p voices config

14
Dockerfile.min
View File

@ -1,11 +1,17 @@
FROM python:3.11-slim
ARG TARGETPLATFORM
RUN apt-get update && apt-get install --no-install-recommends -y curl ffmpeg
RUN if [ "$TARGETPLATFORM" != "linux/amd64" ]; then apt-get install --no-install-recommends -y build-essential ; fi
RUN if [ "$TARGETPLATFORM" != "linux/amd64" ]; then curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y ; fi
RUN <<EOF
apt-get update
apt-get install --no-install-recommends -y curl ffmpeg
if [ "$TARGETPLATFORM" != "linux/amd64" ]; then
apt-get install --no-install-recommends -y build-essential
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
fi
apt-get clean
rm -rf /var/lib/apt/lists/*
EOF
ENV PATH="/root/.cargo/bin:${PATH}"
RUN apt-get clean && rm -rf /var/lib/apt/lists/*
WORKDIR /app
RUN mkdir -p voices config

5
README.md
View File

@ -30,6 +30,11 @@ If you find a better voice match for `tts-1` or `tts-1-hd`, please let me know s
## Recent Changes
Version 0.17.3, 2024-08-15
* fix fr_FR-tom-medium and other 44khz piper voices (detect non-default sample rates)
* minor updates
Version 0.17.2, 2024-07-01
* fix -min image (re: langdetect)

7
pre_process_map.default.yaml
View File

@ -31,7 +31,6 @@
- ' F.Y. '
- - ([0-9]+)-([0-9]+)
- \1 to \2
- - ([0-9]+)[\s]*\*[\s]*([0-9]+)
- \1 times \2
- - '\*'
- ''
# xtts has a lot of trouble with these, but piper is fine.
#- - '[\*=+-]+'
# - ' '