Views
No views yet
.safetensors only (no pickle, no PyTorch 2.6+
weights_only=True gotchas, ~3× smaller than the upstream .pt
because training metadata is dropped). Each file contains the
bare audio-encoder + text-encoder state_dict. Use
safetensors.torch.load_file(path) and
module.model.load_state_dict(sd, strict=False) — the legacy
load_ckpt(ckpt=...) API still works against the upstream .pt
files but not against these.630k-audioset-best.safetensors (variant general, amodel=HTSAT-tiny) — non-fusion HTSAT-tiny checkpoint trained on 630k clips + AudioSet (best validation); amodel='HTSAT-tiny' in laion_clap.CLAP_Module(...).music_audioset_epoch_15_esc_90.14.safetensors (variant music, amodel=HTSAT-base) — music-specialized LAION-CLAP fine-tune; 90.14% on ESC-50; better on music corpora at the cost of marginal regression on speech/SFX. amodel='HTSAT-base' (NOT tiny — the music variant trains a bigger backbone).1import laion_clap
2from safetensors.torch import load_file
3m = laion_clap.CLAP_Module(enable_fusion=False, amodel='HTSAT-tiny')
4sd = load_file('630k-audioset-best.safetensors')
5m.model.load_state_dict(sd, strict=False)
6emb = m.get_audio_embedding_from_data(audio_array_list)