Upload README.md

README.md

@@ -8,16 +8,29 @@ joint-embedding model weights, used by:
 Upstream: https://huggingface.co/lukewys/laion_clap  
 License: CC0-1.0.
 
+## Format
+
+We ship `.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.
+
 ## Files
 
-- `630k-audioset-best.pt` (variant `general`) — non-fusion HTSAT-base checkpoint trained on 630k clips + AudioSet (best validation; `model_id=1` in `laion_clap.CLAP_Module.load_ckpt`).
-- `music_audioset_epoch_15_esc_90.14.pt` (variant `music`) — music-specialized LAION-CLAP fine-tune; 90.14% on ESC-50; better on music corpora at the cost of marginal regression on speech/SFX. Same HTSAT-base + non-fusion architecture as the general checkpoint — drop-in replacement.
+- `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).
 
 ## Loading
 
 ```python
 import laion_clap
-m = laion_clap.CLAP_Module(enable_fusion=False, amodel='HTSAT-base')
-m.load_ckpt(ckpt='630k-audioset-best.pt', verbose=False)
+from safetensors.torch import load_file
+m = laion_clap.CLAP_Module(enable_fusion=False, amodel='HTSAT-tiny')
+sd = load_file('630k-audioset-best.safetensors')
+m.model.load_state_dict(sd, strict=False)
 emb = m.get_audio_embedding_from_data(audio_array_list)
 ```