Views
No views yet
safetensors for minimal inference.lenepa_encoder.safetensors — encoder weights only (no projector, no training/probe state)inference.py — minimal end-to-end inference (no Hydra, no W&B)lenepa_encoder_config.json — fixed IO + architecture contractprovenance.json — original .pt checkpoint path + W&B URLx_waveform: torch.float32 with shape [B, 1, 5000]500 Hz["I"] (so C=1)patch_tokens: [B, 200, 192] (post-final-norm tokens)embedding: [B, 192] (mean pooled over tokens)lenepa_encoder.safetensors from the current directory and prints output shapes):python inference.py1from pathlib import Path
2
3import torch
4
5from inference import encode_lenepa, load_lenepa_encoder
6
7device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
8model = load_lenepa_encoder(weights_path=Path("lenepa_encoder.safetensors"), device=device)
9x = torch.randn(2, 1, 5000, device=device, dtype=torch.float32) # [B, C, L]
10out = encode_lenepa(model=model, x_waveform=x)
11print(out.embedding.shape)