Upload folder using huggingface_hub

README.md

@@ -0,0 +1,34 @@
+---
+language: en
+tags:
+- audio
+- encodec
+- audio-compression
+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
+
+## Usage
+
+```python
+from transformers import AutoProcessor, AutoModel
+import torch
+
+# Load model and processor
+model = AutoModel.from_pretrained("alitair/birdconv_encodec_24khz_1")
+processor = AutoProcessor.from_pretrained("alitair/birdconv_encodec_24khz_1")
+
+# Process audio
+inputs = processor(audio, sampling_rate=24000, return_tensors="pt")
+outputs = model(**inputs)
+```

config.json

@@ -0,0 +1,13 @@
+{
+  "model_type": "encodec",
+  "sample_rate": 24000,
+  "channels": 1,
+  "hidden_size": 128,
+  "num_filters": 32,
+  "kernel_size": 7,
+  "stride": 2,
+  "num_residual_layers": 1,
+  "num_embeddings": 1024,
+  "embedding_dim": 128,
+  "use_conv_shortcut": true
+}

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "chunk_length_s": null,
+  "feature_extractor_type": "EncodecFeatureExtractor",
+  "feature_size": 1,
+  "overlap": null,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 24000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a842d3362114bd9a619050a287219660407494c957b343c3aff67d514dabf37f
+size 93195002