ai-zone/audio-demo
4
0 Fork 0
Code Issues Pull Requests 2 Actions Packages Projects Releases Wiki Activity

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

Browse Source 
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
This commit is contained in:
steve-adminandClaude Sonnet 5 committed 2026-09-12 16:56:25 +00:00
1 parent ff71bd5777
commit 79691b81c6
2 files changed
+35
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

README.md
+12
View File
@@ -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.