admin-valentin/WhisperLiveKit
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

explanations about model persistency in containers

Browse source
This commit is contained in:
Quentin Fuxa 2025-08-29 21:27:08 +02:00 committed by GitHub
parent 42be1a3773
commit 1adac67155
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 15 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
Dockerfile
View file

@ -24,11 +24,11 @@ RUN apt-get update && \
RUN python3 -m venv /opt/venv RUN python3 -m venv /opt/venv
ENV PATH="/opt/venv/bin:$PATH" ENV PATH="/opt/venv/bin:$PATH"
# upgrade pip + setuptools + wheel and increase timeout/retries for large torch wheels # timeout/retries for large torch wheels
RUN pip3 install --upgrade pip setuptools wheel && \ RUN pip3 install --upgrade pip setuptools wheel && \
pip3 --disable-pip-version-check install --timeout=120 --retries=5 \ pip3 --disable-pip-version-check install --timeout=120 --retries=5 \
--index-url https://download.pytorch.org/whl/cu129 \ --index-url https://download.pytorch.org/whl/cu129 \
torch torchvision torchaudio \ torch torchaudio \
|| (echo "Initial install failed — retrying with extended timeout..." && \ || (echo "Initial install failed — retrying with extended timeout..." && \
pip3 --disable-pip-version-check install --timeout=300 --retries=3 \ pip3 --disable-pip-version-check install --timeout=300 --retries=3 \
--index-url https://download.pytorch.org/whl/cu129 \ --index-url https://download.pytorch.org/whl/cu129 \
@ -45,8 +45,20 @@ RUN if [ -n "$EXTRAS" ]; then \
pip install --no-cache-dir whisperlivekit; \ pip install --no-cache-dir whisperlivekit; \
fi fi
# In-container caching for Hugging Face models by:
# A) Make the cache directory persistent via an anonymous volume.
# Note: This only persists for a single, named container. This is
# only for convenience at de/test stage.
# For prod, it is better to use a named volume via host mount/k8s.
VOLUME ["/root/.cache/huggingface/hub"] VOLUME ["/root/.cache/huggingface/hub"]
# or
# B) Conditionally copy a local pre-cache from the build context to the
# container's cache via the HF_PRECACHE_DIR build-arg.
# WARNING: This will copy ALL files in the pre-cache location.
# Conditionally copy a cache directory if provided
RUN if [ -n "$HF_PRECACHE_DIR" ]; then \ RUN if [ -n "$HF_PRECACHE_DIR" ]; then \
echo "Copying Hugging Face cache from $HF_PRECACHE_DIR"; \ echo "Copying Hugging Face cache from $HF_PRECACHE_DIR"; \
mkdir -p /root/.cache/huggingface/hub && \ mkdir -p /root/.cache/huggingface/hub && \
@ -55,6 +67,7 @@ RUN if [ -n "$HF_PRECACHE_DIR" ]; then \
echo "No local Hugging Face cache specified, skipping copy"; \ echo "No local Hugging Face cache specified, skipping copy"; \
fi fi
# Conditionally copy a Hugging Face token if provided. Useful for Diart backend (pyannote audio models)
RUN if [ -n "$HF_TKN_FILE" ]; then \ RUN if [ -n "$HF_TKN_FILE" ]; then \
echo "Copying Hugging Face token from $HF_TKN_FILE"; \ echo "Copying Hugging Face token from $HF_TKN_FILE"; \
mkdir -p /root/.cache/huggingface && \ mkdir -p /root/.cache/huggingface && \