upload spine-codec

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,22 @@
+---
+license: apache-2.0
+pipeline_tag: audio-to-audio
+language:
+- en
+tags:
+- audio
+- audio-codec
+- neural-audio-codec
+- speech-codec
+- speech
+- audio-compression
+- low-bitrate
+- 24khz
+- ddsp
+- fsq
+- gan
+---
+
+# Spine Codec
+
+Model card coming soon.

config.json

@@ -0,0 +1,89 @@
+{
+  "sample_rate": 24000,
+  "encoder_channels": [
+    96,
+    192,
+    384,
+    512,
+    512
+  ],
+  "encoder_rates": [
+    2,
+    4,
+    8,
+    8
+  ],
+  "decoder_channels": [
+    1280,
+    640,
+    320,
+    160,
+    80
+  ],
+  "decoder_rates": [
+    8,
+    8,
+    4,
+    2
+  ],
+  "fsq_levels_per_scale": [
+    [
+      5,
+      5,
+      5,
+      5
+    ],
+    [
+      8,
+      5,
+      5,
+      5,
+      5
+    ],
+    [
+      8,
+      6,
+      5,
+      5,
+      5,
+      5,
+      5,
+      5
+    ],
+    [
+      8,
+      6,
+      5,
+      5,
+      5,
+      5,
+      5,
+      5
+    ]
+  ],
+  "vq_strides": [
+    8,
+    4,
+    2,
+    1
+  ],
+  "transformer_dim": 512,
+  "transformer_mlp_dim": 2048,
+  "transformer_n_heads": 8,
+  "encoder_transformer_n_layers": 8,
+  "decoder_transformer_n_layers": 12,
+  "layerscale_init": 0.01,
+  "use_filtered_snake": true,
+  "filtered_snake_cutoff": 0.25,
+  "filtered_snake_kernel_size": 12,
+  "noise_branch": true,
+  "noise_branch_bands": 64,
+  "noise_branch_n_fft": 2048,
+  "noise_branch_foothold_bias": -3.7,
+  "crossover": true,
+  "crossover_hz": 6000.0,
+  "crossover_taps": 255,
+  "output_bound": null,
+  "hf_head": true,
+  "hf_head_n_fft": 1024
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66b6db52d6a13cf1f9b187938c195f86864971fabeefb0ab92737fdee7b8b060
+size 461650544