Reference and cloned-output wav files are small (~2MB each) and are the
actual evidence of the voice-clone+translate demo working, so track them
despite the general *.wav exclusion.
Co-Authored-By: Claude Sonnet 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01Y1oQ4h4WE4R9KRvMQLr5Ey
Translates a short narrator sentence to Spanish (MarianMT) and
synthesizes it in the narrator's cloned voice (MOSS-TTS
Local-Transformer-v1.5), using a reference clip trimmed from demucs's
isolated vocals stem. First working slice of the full audio-translation
pipeline.
Documents two environment gotchas hit on the RTX 3090: the flagship 8B
checkpoint OOMs on 24GB, and torchaudio/torchcodec fails to load without
manually pulling in nvidia-npp-cu12 and fixing LD_LIBRARY_PATH.
Co-Authored-By: Claude Sonnet 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01Y1oQ4h4WE4R9KRvMQLr5Ey
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
Replaces the 418 MB 1080p source video with a 27 MB 480p derivative and
adds the audio track extracted losslessly from it (AAC stream copy, no
re-encode), which is what the whisperx/demucs/tts demos actually consume.
The full-size source is now gitignored and kept locally only, matching
the existing convention of excluding large binaries from the repo.
Co-Authored-By: Claude Opus 5 <[email protected]>
steve-adminandClaude Sonnet 5
claude-code-pxmx