Bump torch/torchaudio to a Blackwell-compatible version, swap mmcv for mmcv-lite

Root cause of the "CUDA error: no kernel image is available for execution
on the device" failures on every generation: torchaudio==2.5.1+cu124 pinned
torch down to 2.5.1, but HF's own ZeroGPU docs list only 2.8.0-2.11.0 as
supported (https://huggingface.co/docs/hub/spaces-zerogpu#supported-versions)
for their NVIDIA RTX Pro 6000 Blackwell hardware. 2.5.1 predates Blackwell
(sm_120) kernel support entirely, so every single parameter copy onto the
GPU failed identically.

Bumped to torchaudio==2.11.0+cu128 (the top of ZeroGPU's tested range),
verified both torch and torchaudio 2.11.0 wheels exist for cp310 under the
cu128 index. The platform already injects its own `torch<=2.11.0` cap on
the build command line, so no explicit torch pin is needed — it resolves
to match torchaudio's pin.

This orphaned mmcv==2.2.0's --find-links index (only ever published wheels
up through torch2.4.0 — confirmed via direct check, every later torch
directory 404s), which would have ABI-crashed against 2.11.0 since mmcv
ships compiled C++/CUDA extensions. Checked actual usage: TARO's
cavp_modules.py only imports ConvModule/NonLocal3d/build_activation_layer
from mmcv.cnn, all pure-PyTorch model-building wrappers with no compiled
kernels involved (mmcv.ops is never imported). Swapped to mmcv-lite==2.2.0,
the pure-Python distribution with no compiled extensions and thus no
CUDA/torch-version coupling at all.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

requirements.txt

@@ -20,7 +20,6 @@ loguru
 torchdiffeq
 open_clip_torch
 git+https://github.com/descriptinc/audiotools
---extra-index-url https://download.pytorch.org/whl/cu124
-torchaudio==2.5.1+cu124
---find-links https://download.openmmlab.com/mmcv/dist/cu121/torch2.4.0/index.html
-mmcv==2.2.0
+--extra-index-url https://download.pytorch.org/whl/cu128
+torchaudio==2.11.0+cu128
+mmcv-lite==2.2.0