Prepare for pypi release (#6)

* update versions + deps

* update readme

* add programmatic usage section

* lint correction

* bug fix for odd strikes

Author: eeishaan

.gitignore

@@ -172,5 +172,5 @@ archived/
 *.zip
 *.pth
 encoded_out/
-recon/ 
+recon/
 recons/

README.md

@@ -22,9 +22,12 @@ neural audio codec, introduced in the paper titled **High-Fidelity Audio Compres
 
 ### Installation
 ```
-git clone https://github.com/descriptinc/descript-audio-codec
-cd descript-audio-codec
-pip install .
+pip install descript-audio-codec
+```
+OR
+
+```
+pip install git+https://github.com/descriptinc/descript-audio-codec
 ```
 
 ### Weights
@@ -36,7 +39,6 @@ python3 -m dac download
 We provide a Dockerfile that installs all required dependencies for encoding and decoding. The build process caches model weights inside the image. This allows the image to be used without an internet connection. [Please refer to instructions below.](#docker-image)
 
 
-
 ### Compress audio
 ```
 python3 -m dac encode /path/to/input --output /path/to/output/codes
@@ -57,6 +59,38 @@ It will also preserve the directory structure relative to input root and
 re-create it in the output directory. Please use `python -m dac decode --help`
 for more options.
 
+### Programmatic Usage
+```py
+import dac
+from dac.utils import load_model
+from dac.model import DAC
+
+from dac.utils.encode import process as encode
+from dac.utils.decode import process as decode
+
+from audiotools import AudioSignal
+
+# Init an empty model
+model = DAC()
+
+# Load compatible pre-trained model
+model = load_model(dac.__model_version__)
+model.eval()
+model.to('cuda')
+
+# Load audio signal file
+signal = AudioSignal('input.wav')
+
+# Encode audio signal
+encoded_out = encode(signal, 'cuda', model)
+
+# Decode audio signal
+recon = decode(encoded_out, 'cuda', model, preserve_sample_rate=True)
+
+# Write to file
+recon.write('recon.wav')
+```
+
 ### Docker image
 We provide a dockerfile to build a docker image with all the necessary
 dependencies.

dac/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "0.0.1"
+__version__ = "0.0.2"
 __model_version__ = "0.0.1"
 import audiotools
 

dac/__main__.py

@@ -25,7 +25,6 @@ def run(stage: str):
         stage_fn()
         return
 
-
     stage_fn()
 
 

dac/model/dac.py

@@ -49,7 +49,7 @@ def __init__(self, dim: int = 16, stride: int = 1):
                 dim,
                 kernel_size=2 * stride,
                 stride=stride,
-                padding=stride // 2,
+                padding=math.ceil(stride / 2),
             ),
         )
 
@@ -96,7 +96,7 @@ def __init__(self, input_dim: int = 16, output_dim: int = 8, stride: int = 1):
                 output_dim,
                 kernel_size=2 * stride,
                 stride=stride,
-                padding=stride // 2,
+                padding=math.ceil(stride / 2),
             ),
             ResidualUnit(output_dim, dilation=1),
             ResidualUnit(output_dim, dilation=3),

setup.py

@@ -6,7 +6,7 @@
 
 setup(
     name="dac",
-    version="0.0.1",
+    version="0.0.2",
     classifiers=[
         "Intended Audience :: Developers",
         "Natural Language :: English",
@@ -28,7 +28,7 @@
     keywords=["audio", "compression", "machine learning"],
     install_requires=[
         "argbind>=0.3.7",
-        "audiotools @ git+https://github.com/descriptinc/audiotools.git@0.7.0",
+        "descript-audiotools==0.7.1",
         "einops",
         "numpy",
         "torch",