From 1e6f8bc984ff734487bfaa3fcb6e6d053a31a587 Mon Sep 17 00:00:00 2001 From: Steve Calcott Date: Fri, 11 Sep 2026 16:42:41 +0000 Subject: [PATCH] Add starter structure for demucs/tts demos and .gitignore Co-Authored-By: Claude Sonnet 5 Claude-Session: https://claude.ai/code/session_01SN15Vxn4svKuhYxFsVtMJf --- .gitignore | 27 +++++++++++++++++++++++++++ README.md | 14 +++++++++++++- demucs/README.md | 3 +++ tts/README.md | 3 +++ 4 files changed, 46 insertions(+), 1 deletion(-) create mode 100644 .gitignore create mode 100644 demucs/README.md create mode 100644 tts/README.md diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..29ad255 --- /dev/null +++ b/.gitignore @@ -0,0 +1,27 @@ +.env + +# Python +__pycache__/ +*.pyc +.venv/ +venv/ + +# Model weights / large artifacts +*.pt +*.ckpt +*.bin +*.safetensors +models/ +weights/ + +# Audio I/O scratch +*.wav +*.mp3 +*.flac +output/ +outputs/ + +# OS/editor +.DS_Store +.idea/ +.vscode/ diff --git a/README.md b/README.md index a28aa1b..cf8c4a8 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,15 @@ # audio-demo -Audio processing demos: WhisperX, Demucs, and TTS technology proofs-of-concept. \ No newline at end of file +Audio processing demos: WhisperX, Demucs, and TTS technology proofs-of-concept. + +## Structure + +- `whisperx/` — speech-to-text with word-level alignment and diarization +- `demucs/` — source separation (vocals/instrumentals stem splitting) +- `tts/` — text-to-speech service demos + +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). diff --git a/demucs/README.md b/demucs/README.md new file mode 100644 index 0000000..a1f3f13 --- /dev/null +++ b/demucs/README.md @@ -0,0 +1,3 @@ +# demucs + +Source separation demos using [Demucs](https://github.com/facebookresearch/demucs) — splitting audio into stems (vocals, drums, bass, other). diff --git a/tts/README.md b/tts/README.md new file mode 100644 index 0000000..0451ccb --- /dev/null +++ b/tts/README.md @@ -0,0 +1,3 @@ +# tts + +Text-to-speech service demos and proofs-of-concept.