mirror of
https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI.git
synced 2026-06-05 01:10:22 +08:00
1e22d468ea
* feat(audio): use PyAV instead of ffmpeg replaced usage of ffmpeg in favor of PyAV (`av`) * refactor(audio): store all of the audio related functions in the `infer.lib.audio` refactors previous commit to have singular functions for each task, all located in `infer.lib.audio` * fix(audio): remove downsample_audio from mdxnet.py it is no longer needed, since it's imported from infer.lib.audio * docs: remove every ffmpeg mention in the documentation to avoid confusion * chore(requirements): remove ffmpeg-python and ffmpy from all requirements * fix(audio): fix loading for UVR wrapped gathering of META info from the stream into a function fixes loading for UVR * fix(audio): use np.frombuffer() instead of direct conversion of the resampled frames this fixes traceback on preprocessing * feat(audio): pre-allocate decoded_audio array in the load_audio function this should improve performance, even if just a little * Revert "docs: remove every ffmpeg mention in the documentation to avoid confusion" This reverts commit1e05bbce03. * chore(format): run black on dev * fix(requirements): revert removal of ffmpeg in unitest.yml and Dockerfile * Revert "fix(requirements): revert removal of ffmpeg in unitest.yml and Dockerfile" This reverts commite28a0eebb2. * feat(audio): pre-allocate numpy array to store the AudioFrame data in ndarray of dtype float32 * chore(format): run black on dev * fix(audio): fix the decoded_audio size estimation in estimated_total_samples we multiply by `sr` instead of `container.streams.audio[0].rate` since we want to estimate size of the OUTPUT file, not the input one. - Added dynamic resizing, in case something goes wrong and the size of decoded_audio is estimated incorrectly Fixed function `load_audio` when the input audio's samplerate does not match the desired samplerate (`sr`) * chore(format): run black on dev * refactor(audio): remove `clean_path()` function as it serves no purpose anymore * docs: remove everything related to ffmpeg this includes everything except for formats support specification in the training_tips docs, since it has nothing to do with what ffmpeg does/did but rather what audio formats are supported (all the ones that ffmpeg supports!) * docs: fix order of the steps in preparation in the READMEs --------- Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
47 lines
2.5 KiB
Docker
47 lines
2.5 KiB
Docker
# syntax=docker/dockerfile:1
|
|
|
|
FROM nvidia/cuda:11.6.2-cudnn8-runtime-ubuntu20.04
|
|
|
|
EXPOSE 7865
|
|
|
|
WORKDIR /app
|
|
|
|
# Install dependenceis to add PPAs
|
|
RUN apt-get update && \
|
|
apt-get install -y -qq aria2 && apt clean && \
|
|
apt-get install -y software-properties-common && \
|
|
apt-get clean && \
|
|
rm -rf /var/lib/apt/lists/*
|
|
# Add the deadsnakes PPA to get Python 3.9
|
|
RUN add-apt-repository ppa:deadsnakes/ppa
|
|
|
|
# Install Python 3.9 and pip
|
|
RUN apt-get update && \
|
|
apt-get install -y build-essential python-dev python3-dev python3.9-distutils python3.9-dev python3.9 curl && \
|
|
apt-get clean && \
|
|
update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.9 1 && \
|
|
curl https://bootstrap.pypa.io/get-pip.py | python3.9
|
|
|
|
# Set Python 3.9 as the default
|
|
RUN update-alternatives --install /usr/bin/python python /usr/bin/python3.9 1
|
|
|
|
COPY . .
|
|
|
|
RUN python3 -m pip install --no-cache-dir -r requirements/main.txt
|
|
|
|
RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/D40k.pth -d assets/pretrained_v2/ -o D40k.pth
|
|
RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/G40k.pth -d assets/pretrained_v2/ -o G40k.pth
|
|
RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0D40k.pth -d assets/pretrained_v2/ -o f0D40k.pth
|
|
RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0G40k.pth -d assets/pretrained_v2/ -o f0G40k.pth
|
|
|
|
RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP2-人声vocals+非人声instrumentals.pth -d assets/uvr5_weights/ -o HP2-人声vocals+非人声instrumentals.pth
|
|
RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP5-主旋律人声vocals+其他instrumentals.pth -d assets/uvr5_weights/ -o HP5-主旋律人声vocals+其他instrumentals.pth
|
|
|
|
RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt -d assets/hubert -o hubert_base.pt
|
|
|
|
RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/rmvpe.pt -d assets/rmvpe -o rmvpe.pt
|
|
|
|
VOLUME [ "/app/weights", "/app/opt" ]
|
|
|
|
CMD ["python3", "web.py"]
|