bass-transcribelisted

# Bass Transcribe — played take → MIDI / Live clip / chart Default is the offline **CREPE** pipeline (validated: CREPE `full`+viterbi beats pyin on bass and vocals). For in-Live plugin options (NeuralNote, Jam Origin) read `references/realtime-options.md`. ## 1. Get the audio - **User points at a file** — wav/mp3/aiff of the take. Mono preferred; DI cleaner than mic. - **Record in Live** — audio track, arm, record the take. MCP **cannot export audio**: the user does File → Export, or point at the raw recording under the Set's `Samples/Recorded/` folder. - Ask for (or detect) the take's **BPM** if the output will go into a Live clip. ## 2. Default pipeline — CREPE → MIDI ```python import crepe, librosa, numpy as np, pretty_midi y, sr = librosa.load(AUDIO, sr=16000, mono=True) time, freq, conf, _ = crepe.predict(y, sr, model_capacity='full', viterbi=True, step_size=10) CONF, MIN_LEN, GAP = 0.55, 0.08, 0.05 # confidence gate, min note s, merge gap s midi_f = 69 + 12*np.log2(freq/440.0) notes, cur = [], None for t, m, c in zip(time, midi_f, conf): p = int(round(m)) if c >= CONF and np.isfinite(m) else None if cur and p == cur['p'] and t - cur['end'] <= GAP: cur['end'] = t else: if cur and cur['end'] - cur['start'] >= MIN_LEN: notes.append(cur) cur = {'p': p, 'start': t, 'end': t} if p is not None else None if cur and cur['end'] - cur['start'] >= MIN_LEN: notes.append(cur) pm = pretty_midi.PrettyMIDI() inst = pretty