Add demucs stem-separation demo; sketch audio-translation pipeline

Two-stem separation (vocals/instrumental) run on RTX 3090 against the
shared sample clip. Isolated vocals.wav is meant as the clean voice
reference for a future voice-cloning TTS step.

Co-Authored-By: Claude Sonnet 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01Y1oQ4h4WE4R9KRvMQLr5Ey

README.md

@@ -13,3 +13,15 @@ Each subdirectory has its own README with setup and run instructions.
 ## Requirements
 
 Some demos are GPU-accelerated and are best run on a CUDA-capable machine (e.g. an RTX 3090).
+
+## Planned: full audio-translation demo
+
+Chain the three demos together on `media-files/` into an end-to-end pipeline:
+
+1. `demucs` — separate the source clip into vocals / instrumental stems
+2. `whisperx` — transcribe the isolated vocal stem, then machine-translate the transcript
+3. `tts` — clone the original speaker's voice (from the isolated vocal stem) and synthesize
+   the translated text in that voice, then remix with the original instrumental stem
+
+Stem separation and transcription are already working end to end (see `demucs/README.md` and
+`whisperx/README.md`); translation and voice-cloning TTS are not yet implemented.

demucs/README.md

@@ -1,3 +1,26 @@
 # demucs
 
 Source separation demos using [Demucs](https://github.com/facebookresearch/demucs) — splitting audio into stems (vocals, drums, bass, other).
+
+## Demo run
+
+Ran two-stem separation (vocals vs. everything else) on an RTX 3090 against
+`media-files/audio/service-mbrs-ntscrm-01840194-01840194.m4a`:
+
+```
+python3 -m demucs --two-stems=vocals -n htdemucs \
+  -o separated \
+  ../media-files/audio/service-mbrs-ntscrm-01840194-01840194.m4a
+```
+
+Took ~12s for 11 minutes of audio. Outputs `vocals.wav` and `no_vocals.wav` (44.1kHz stereo PCM,
+duration matches source) under `separated/htdemucs/<track-name>/` — gitignored, left on the GPU
+box at `/root/projects/audio-demo/repo/demucs/separated/`.
+
+**Known gotcha:** demucs 4.1.0's package metadata doesn't declare `numpy` as a dependency even
+though `demucs/transformer.py` imports it directly — `pip install demucs` alone leaves the env
+broken (`ModuleNotFoundError: No module named 'numpy'` at runtime). Install `numpy` explicitly
+alongside it.
+
+The isolated `vocals.wav` is intended as the clean reference/source audio for a voice-cloning TTS
+step (see top-level README for the planned audio-translation pipeline).