# 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. Pinning to v2.5.1 — the
# last torchaudio tag that builds cleanly against torch 2.5–2.10 and is a
# proven compatibility target.
ENV USE_CUDA=1 BUILD_SOX=0 TORCH_CUDA_ARCH_LIST="9.0;10.0;12.0"
RUN pip install --break-system-packages --no-cache-dir \
    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"]