From 0a49fafa0de3877829b480ac6a54686bdfc7ca30 Mon Sep 17 00:00:00 2001
From: Rahul Mourya <mouryarahul543@gmail.com>
Date: Sat, 30 Aug 2025 00:23:59 +0530
Subject: [PATCH 1/2] Update Dockerfile

fix(docker): increase pip timeout/retries for PyTorch wheel installs
---
 Dockerfile | 38 ++++++++++++++------------------------
 1 file changed, 14 insertions(+), 24 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index 580aa92..f01384d 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -17,18 +17,26 @@ RUN apt-get update && \
         ffmpeg \
         git \
         build-essential \
-        python3-dev && \
+        python3-dev \
+        ca-certificates && \
     rm -rf /var/lib/apt/lists/*
 
 RUN python3 -m venv /opt/venv
 ENV PATH="/opt/venv/bin:$PATH"
-RUN pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu129
+
+# upgrade pip + setuptools + wheel and increase timeout/retries for large torch wheels
+RUN pip3 install --upgrade pip setuptools wheel && \
+    pip3 --disable-pip-version-check install --timeout=120 --retries=5 \
+        --index-url https://download.pytorch.org/whl/cu129 \
+        torch torchvision torchaudio \
+    || (echo "Initial install failed — retrying with extended timeout..." && \
+        pip3 --disable-pip-version-check install --timeout=300 --retries=3 \
+            --index-url https://download.pytorch.org/whl/cu129 \
+            torch torchvision torchaudio)
 
 COPY . .
 
 # Install WhisperLiveKit directly, allowing for optional dependencies
-#   Note: For gates models, need to add your HF toke. See README.md
-#         for more details.
 RUN if [ -n "$EXTRAS" ]; then \
       echo "Installing with extras: [$EXTRAS]"; \
       pip install --no-cache-dir whisperlivekit[$EXTRAS]; \
@@ -37,22 +45,8 @@ RUN if [ -n "$EXTRAS" ]; then \
       pip install --no-cache-dir whisperlivekit; \
     fi
 
-# Enable in-container caching for Hugging Face models by: 
-# Note: If running multiple containers, better to map a shared
-# bucket. 
-#
-# 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"]
 
-# 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 \
       echo "Copying Hugging Face cache from $HF_PRECACHE_DIR"; \
       mkdir -p /root/.cache/huggingface/hub && \
@@ -61,8 +55,6 @@ RUN if [ -n "$HF_PRECACHE_DIR" ]; then \
       echo "No local Hugging Face cache specified, skipping copy"; \
     fi
 
-# Conditionally copy a Hugging Face token if provided
-
 RUN if [ -n "$HF_TKN_FILE" ]; then \
       echo "Copying Hugging Face token from $HF_TKN_FILE"; \
       mkdir -p /root/.cache/huggingface && \
@@ -70,11 +62,9 @@ RUN if [ -n "$HF_TKN_FILE" ]; then \
     else \
       echo "No Hugging Face token file specified, skipping token setup"; \
     fi
-    
-# Expose port for the transcription server
+
 EXPOSE 8000
 
 ENTRYPOINT ["whisperlivekit-server", "--host", "0.0.0.0"]
 
-# Default args
-CMD ["--model", "medium"]
\ No newline at end of file
+CMD ["--model", "medium"]

From 1adac671557d818caf4ce3f97c0ff521afea595e Mon Sep 17 00:00:00 2001
From: Quentin Fuxa <38427957+QuentinFuxa@users.noreply.github.com>
Date: Fri, 29 Aug 2025 21:27:08 +0200
Subject: [PATCH 2/2] explanations about model persistency in containers

---
 Dockerfile | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index f01384d..534f99d 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -24,11 +24,11 @@ RUN apt-get update && \
 RUN python3 -m venv /opt/venv
 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 && \
     pip3 --disable-pip-version-check install --timeout=120 --retries=5 \
         --index-url https://download.pytorch.org/whl/cu129 \
-        torch torchvision torchaudio \
+        torch torchaudio \
     || (echo "Initial install failed — retrying with extended timeout..." && \
         pip3 --disable-pip-version-check install --timeout=300 --retries=3 \
             --index-url https://download.pytorch.org/whl/cu129 \
@@ -45,8 +45,20 @@ RUN if [ -n "$EXTRAS" ]; then \
       pip install --no-cache-dir whisperlivekit; \
     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"]
 
+
+# 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 \
       echo "Copying Hugging Face cache from $HF_PRECACHE_DIR"; \
       mkdir -p /root/.cache/huggingface/hub && \
@@ -55,6 +67,7 @@ RUN if [ -n "$HF_PRECACHE_DIR" ]; then \
       echo "No local Hugging Face cache specified, skipping copy"; \
     fi
 
+# Conditionally copy a Hugging Face token if provided. Useful for Diart backend (pyannote audio models)
 RUN if [ -n "$HF_TKN_FILE" ]; then \
       echo "Copying Hugging Face token from $HF_TKN_FILE"; \
       mkdir -p /root/.cache/huggingface && \