Keysat
a24610ad2a
Build was crashing inside torchaudio's setup.py with:
ModuleNotFoundError: No module named 'torch'
PIP_CONSTRAINT was correctly pinning torch/torchvision in the install
target env, but pip's PEP 517 build isolation creates a SEPARATE fresh
Python env just for the build wheel step — and that env has no torch
in it. torchaudio's setup.py imports torch to discover CUDA flags, so
it crashes. Pip even printed a deprecation warning that this isolation
behavior is hardening, not relaxing.
Fix:
1. Pre-install torchaudio's build deps (setuptools, wheel, ninja,
pybind11) into the main env since we're disabling isolation.
2. Add --no-build-isolation to the torchaudio install so the build
uses NGC's torch directly.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
97 lines
4.7 KiB
Docker
97 lines
4.7 KiB
Docker
# WhisperX ASR + diarization container for Spark 2 (Blackwell GB10, sm_120).
|
|
#
|
|
# Replaces the custom Parakeet wrapper + Sortformer overlay with a single
|
|
# mainline pipeline: faster-whisper for transcription + pyannote.audio 3.1
|
|
# for diarization + wav2vec2 forced alignment for word-level timestamps.
|
|
#
|
|
# Build (on Spark 2, where Blackwell + nvcr.io credentials are available):
|
|
# docker build -t whisperx-asr:latest .
|
|
#
|
|
# Run:
|
|
# docker run -d --restart unless-stopped --name whisperx-asr \
|
|
# --gpus all --memory=40g \
|
|
# -p 8002:8002 \
|
|
# -v whisperx-models:/root/.cache/huggingface \
|
|
# -e HF_TOKEN="$(cat ~/.cache/huggingface/token)" \
|
|
# -e WHISPER_MODEL=medium \
|
|
# whisperx-asr:latest
|
|
#
|
|
# The memory cap is intentional: even if WhisperX hits a pathological input,
|
|
# it gets OOM-killed cleanly instead of swap-thrashing the whole Spark.
|
|
|
|
FROM nvcr.io/nvidia/pytorch:25.11-py3
|
|
|
|
# WhisperX runs ffmpeg under the hood for audio decoding.
|
|
# git + cmake + build-essential are needed to build torchaudio from source
|
|
# (see below); we remove them at the end of the next layer to keep the image
|
|
# from growing unnecessarily.
|
|
RUN apt-get update \
|
|
&& apt-get install -y --no-install-recommends \
|
|
ffmpeg git cmake build-essential ninja-build \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
# Pin torch + torchvision to whatever NGC actually shipped so pip can't swap
|
|
# them out when it satisfies whisperx/pyannote deps. (NGC's torch is a custom
|
|
# build with a non-standard local version like "2.10.0a0+b558c986e8.nv25.11"
|
|
# — stock pip wheels would clobber it and break the ABI.)
|
|
RUN python3 -c "import torch, torchvision; \
|
|
import sys; \
|
|
sys.stdout.write(f'torch=={torch.__version__}\ntorchvision=={torchvision.__version__}\n')" \
|
|
> /tmp/torch-constraints.txt \
|
|
&& echo '── pinned torch versions ──' && cat /tmp/torch-constraints.txt
|
|
|
|
# NGC PyTorch images don't include torchaudio (NVIDIA optimizes for
|
|
# vision/text workloads). Stock torchaudio wheels are ABI-incompatible with
|
|
# NGC's custom torch 2.10a, so the only working option is building from
|
|
# source against the NGC torch already in the image.
|
|
#
|
|
# Build env knobs:
|
|
# USE_CUDA=1 — build CUDA kernels (we have a GPU)
|
|
# BUILD_SOX=0 — skip libsox (we only use audio decoding)
|
|
# TORCH_CUDA_ARCH_LIST=... — build kernels for Hopper + Blackwell datacenter
|
|
# + Blackwell consumer (sm_120 = GB10)
|
|
# --no-build-isolation — CRITICAL: PEP 517 build isolation creates a
|
|
# fresh env with no torch in it. torchaudio's
|
|
# setup.py imports torch to discover the build
|
|
# flags, so it crashes without this flag.
|
|
# With it, the build uses NGC's torch directly.
|
|
ENV USE_CUDA=1 BUILD_SOX=0 TORCH_CUDA_ARCH_LIST="9.0;10.0;12.0"
|
|
# Pre-install torchaudio's build-time deps (PEP 517 would normally install
|
|
# these in the isolated build env, but we just turned isolation off).
|
|
RUN pip install --break-system-packages --no-cache-dir \
|
|
"setuptools>=61" wheel ninja "pybind11>=2.10"
|
|
RUN pip install --break-system-packages --no-cache-dir --no-build-isolation \
|
|
git+https://github.com/pytorch/audio.git@v2.5.1 \
|
|
&& python3 -c "import torchaudio; print('torchaudio built:', torchaudio.__version__)"
|
|
|
|
# Append torchaudio to constraints so pip can't replace it later.
|
|
RUN python3 -c "import torchaudio; print(f'torchaudio=={torchaudio.__version__}')" \
|
|
>> /tmp/torch-constraints.txt \
|
|
&& echo '── final pinned versions ──' && cat /tmp/torch-constraints.txt
|
|
|
|
# Install whisperx + the FastAPI wrapper deps under the torch+torchaudio
|
|
# constraint. pip will satisfy whisperx/pyannote without swapping any of the
|
|
# pytorch-family packages.
|
|
COPY requirements.txt /tmp/requirements.txt
|
|
RUN pip install --break-system-packages --no-cache-dir \
|
|
-c /tmp/torch-constraints.txt -r /tmp/requirements.txt
|
|
|
|
# Pre-warm the default Whisper + alignment models at build time so first-call
|
|
# latency on a fresh container is small. (~3 GB cached into the image; if you
|
|
# want a smaller image, comment this out and accept the first-call download.)
|
|
ARG WHISPER_MODEL=medium
|
|
ENV WHISPER_MODEL=${WHISPER_MODEL}
|
|
RUN python3 -c "import whisperx; whisperx.load_model('${WHISPER_MODEL}', 'cpu', compute_type='int8')" \
|
|
&& python3 -c "import whisperx; whisperx.load_align_model(language_code='en', device='cpu')"
|
|
|
|
WORKDIR /opt/whisperx
|
|
COPY app /opt/whisperx/app
|
|
|
|
# Expose for spark-control's proxy on Spark 2
|
|
EXPOSE 8002
|
|
|
|
HEALTHCHECK --interval=30s --timeout=10s --start-period=180s \
|
|
CMD python3 -c "import urllib.request; urllib.request.urlopen('http://localhost:8002/health')" || exit 1
|
|
|
|
CMD ["python3", "-m", "uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8002", "--workers", "1"]
|