Fabio
c36510c21e
Some checks failed
Linux Build / Linux cpu (push) Has been cancelled
Linux Build / Linux cpu-clang (push) Has been cancelled
Linux Build / Linux vulkan (push) Has been cancelled
mac-build / macOS CPU (push) Has been cancelled
Nix Build / Nix (cpu) (push) Has been cancelled
Nix Build / Nix (vulkan) (push) Has been cancelled
windows-build / Windows CPU (push) Has been cancelled
41 lines
2 KiB
Markdown
41 lines
2 KiB
Markdown
# Real-time RE-USE validation
|
|
|
|
Use the original checkpoint from
|
|
[nvidia/Real-time_RE-USE](https://huggingface.co/nvidia/Real-time_RE-USE/tree/4c0c186272ca853cd18d832fc5c28777b62f32d1).
|
|
The converter checks its SHA256 and verifies the complete tensor inventory, shapes,
|
|
and retained F32 tensor bytes after packaging.
|
|
|
|
```bash
|
|
python tests/realtime_reuse/convert_gguf.py --source SOURCE \
|
|
--output models/Real-time-RE-USE-GGUF/realtime-reuse-f32.gguf \
|
|
--log conversion.log
|
|
```
|
|
|
|
`run_python_reference.py --help` describes reference generation with the original
|
|
Python implementation. Use `--no-tf32` for the strict F32 waveform comparison;
|
|
leave that diagnostic switch off for ordinary Python performance measurements.
|
|
`--reference-file reference.safetensors` exports the waveform, frontend features,
|
|
and expected restored waveform together with the selected configuration.
|
|
|
|
```bash
|
|
build/debug/bin/test_realtime_reuse_reference \
|
|
--model models/Real-time-RE-USE-GGUF/realtime-reuse-f32.gguf \
|
|
--reference reference.safetensors --backend cuda --log --log-file parity.log
|
|
|
|
build/debug/bin/test_realtime_reuse_streaming \
|
|
--model models/Real-time-RE-USE-GGUF/realtime-reuse-f32.gguf \
|
|
--audio noisy.wav --backend cuda --sample-rate 8000 --all-configs \
|
|
--log --log-file streaming.log
|
|
```
|
|
|
|
The reference test compares the final waveform after supplying the official
|
|
frontend features to the C++ network (cosine greater than 0.99999). It also logs
|
|
frontend differences separately. The streaming test covers all 30 exit/lookahead
|
|
combinations, checks early emission, input-fragmentation invariance, exact sample
|
|
counts, finite samples, long-short-long repeatability, and streaming/offline
|
|
waveform similarity through the 1→2→4→8 frame batch transitions and the padded
|
|
final batch. The first 40 ms are excluded from the last comparison because
|
|
upstream online inference deliberately skips the first-frame sweep filter.
|
|
|
|
`cli_cases.json` supplies offline, streaming, request-reuse, and long-form cases
|
|
for the existing CLI path runner. Run resource measurements sequentially.
|