pytheory

mirror of https://github.com/kennethreitz/pytheory.git synced 2026-06-21 15:00:57 +00:00

Files

T

kennethreitz 63390cb7c7 Full-mix transcription, auto tempo, native voice memos — v0.46.0

- Score.from_wav(split=True): harmonic-percussive separation (median-
  filtered spectrogram masks) + band-split passes → bass and melody parts
- Automatic tempo estimation from onset autocorrelation (bpm=None default)
- .m4a/.mp3 load directly via afconvert/ffmpeg
- Fix stereo int16/int32 WAV normalization (dtype check ran after mixdown)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

2026-06-12 01:40:14 -04:00

_static

Add sound examples for hard sync, ring mod, wavefold, drift, karplus-strong, mellotron docs

2026-04-04 14:04:37 -04:00

_templates

Add audio samples for documentation

2026-03-29 05:42:34 -04:00

api

11x faster rendering, live-mode fixes, docs overhaul — v0.44.0

2026-06-12 00:27:27 -04:00

guide

Full-mix transcription, auto tempo, native voice memos — v0.46.0