Upload folder using huggingface_hub

README.md

@@ -9,26 +9,15 @@ license: mit
 
 # alitair/birdconv_encodec_24khz_1
 
-This is an EnCodec model fine-tuned for audio compression.
-
-## Model Description
-
-- **Model type:** EnCodec
-- **Sample rate:** 24kHz
-- **Channels:** 1 (mono)
-- **Base model:** facebook/encodec_24khz
+This repository contains weights for a fine-tuned EnCodec model trained using AudioCraft.
 
 ## Usage
 
 ```python
-from transformers import AutoProcessor, AutoModel
-import torch
+from audiocraft.models import CompressionModel
+from transformers import AutoProcessor
 
 # Load model and processor
-model = AutoModel.from_pretrained("alitair/birdconv_encodec_24khz_1")
+model = CompressionModel.get_pretrained("alitair/birdconv_encodec_24khz_1/compression_state_dict.bin")
 processor = AutoProcessor.from_pretrained("alitair/birdconv_encodec_24khz_1")
-
-# Process audio
-inputs = processor(audio, sampling_rate=24000, return_tensors="pt")
-outputs = model(**inputs)
 ```

compression_state_dict.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48d8c72ca8e6fbc00ac9b303cc12958ef27d956e9b81370296af46cc08de4f72
+size 92470530