stacks/index-tts: revert git-lfs build attempt; document the LFS

budget hazard + media-CDN workaround

Tried adding git-lfs install + git lfs pull to the build to get
real example WAVs into the image — failed with:

    Error downloading object: examples/emo_hate.wav: Smudge error:
    batch response: This repository exceeded its LFS budget. The
    account responsible for the budget should increase it to
    restore access.

The index-tts org's LFS bandwidth quota is exhausted upstream and
out of our control. Reverting the Dockerfile change. The examples
aren't needed for the wrapper to work; emotion_text and
emotion_vector are sufficient for end-to-end testing without any
WAV file at all.

For users who want the bundled example clips as starter audio,
README now documents the media-CDN URL trick — same LFS objects
served via a different code path that doesn't count against the
LFS API budget. INDEX_TTS_TAG stays at v1.

stacks/index-tts/.env.example

@@ -6,10 +6,8 @@
 INDEX_TTS_SHA=830f6f8f94a51fea23ab1d639027a86200075a4e
 
 # Local image tag — bump when you change build context (Dockerfile,
-# app.py, entrypoint.sh) to force a fresh layer build. v2 = git-lfs
-# added so the example WAVs in /opt/index-tts/examples/ come down as
-# real audio (v1 left them as LFS pointer stubs).
-INDEX_TTS_TAG=v2
+# app.py, entrypoint.sh) to force a fresh layer build.
+INDEX_TTS_TAG=v1
 
 # ── network ──────────────────────────────────────────────────────────
 # Host port. Container listens on 8000 internally.

stacks/index-tts/Dockerfile

@@ -15,25 +15,28 @@ ENV DEBIAN_FRONTEND=noninteractive \
 RUN apt-get update \
  && apt-get install -y --no-install-recommends \
         python3.10 python3.10-venv python3-pip \
-        git git-lfs ffmpeg libsndfile1 \
+        git ffmpeg libsndfile1 \
         ca-certificates wget \
  && rm -rf /var/lib/apt/lists/* \
- && python3.10 -m venv /opt/venv \
- && git lfs install --system
+ && python3.10 -m venv /opt/venv
 
 # Pinned IndexTTS-2 SHA — bump in stack .env (INDEX_TTS_SHA build arg)
 # when you want upstream updates.
 #
-# `git lfs pull` after the checkout fetches examples/emo_*.wav and the
-# example/voice_*.wav reference clips that are stored as LFS objects.
-# Without it, the .wav files come down as ~130-byte LFS pointer text
-# files, and `docker cp`-ing them out as starter material for
-# /worktank/index-tts/{voices,emotions} produces unusable garbage.
+# Note on LFS: examples/emo_*.wav and examples/voice_*.wav in the
+# upstream repo are Git LFS objects, but the index-tts org has
+# repeatedly exhausted GitHub's LFS bandwidth budget — `git lfs pull`
+# in the build aborts with "This repository exceeded its LFS budget".
+# We don't need the examples for the wrapper to work; they're just
+# convenient starter audio. To stage real LFS-backed examples on the
+# host, fetch them once via the media CDN (a different code path that
+# doesn't count against the LFS API budget):
+#
+#   curl -fsSL -o /worktank/index-tts/emotions/hate.wav \
+#     https://media.githubusercontent.com/media/index-tts/index-tts/main/examples/emo_hate.wav
 ARG INDEX_TTS_SHA=830f6f8f94a51fea23ab1d639027a86200075a4e
 RUN git clone https://github.com/index-tts/index-tts.git /opt/index-tts \
- && cd /opt/index-tts \
- && git checkout ${INDEX_TTS_SHA} \
- && git lfs pull
+ && cd /opt/index-tts && git checkout ${INDEX_TTS_SHA}
 
 # CUDA 12.8 torch wheels (per IndexTTS pyproject.toml's tool.uv.index
 # pin — same versions, same source).

stacks/index-tts/README.md

@@ -127,6 +127,22 @@ ssh irv-ml1 '
 - **Model download** — happens in the entrypoint on first start; the
   config.yaml file in the cache dir is the gate. To force a re-download,
   delete that file and recreate the container.
+- **Bundled example WAVs are LFS pointers, not audio.** Upstream stores
+  `examples/emo_*.wav` and `examples/voice_*.wav` as Git LFS objects.
+  The image clones the repo without `git lfs pull` (the index-tts org
+  has exhausted GitHub's LFS bandwidth budget repeatedly, so doing it
+  in the Dockerfile aborts the build). If you want the IndexTTS-2
+  example clips as starter material, fetch them once via the media
+  CDN — that's a separate code path that doesn't count against the
+  LFS API budget:
+
+  ```bash
+  ssh irv-ml1 '
+    cd /worktank/index-tts/emotions
+    curl -fsSL -o hate.wav https://media.githubusercontent.com/media/index-tts/index-tts/main/examples/emo_hate.wav
+    curl -fsSL -o sad.wav  https://media.githubusercontent.com/media/index-tts/index-tts/main/examples/emo_sad.wav
+  '
+  ```
 - **HF cache pinning** — `infer_v2.py` pins `HF_HUB_CACHE` at import
   time to `./checkpoints/hf_cache`. The wrapper sets this env var
   before importing, so auxiliary HF assets (MaskGCT, campplus, BigVGAN,