Add simple API call (facebookresearch#474)

* Accept simple API Call

* Fix typo

README.md

@@ -242,6 +242,20 @@ If you want to use GPU acceleration, you will need at least 3GB of RAM on your G
 
 If you do not have enough memory on your GPU, simply add `-d cpu` to the command line to use the CPU. With Demucs, processing time should be roughly equal to 1.5 times the duration of the track.
 
+## Calling from another Python program
+
+The main function provides a `opt` parameter as a simple API. You can just pass the parsed command line as this parameter: 
+```python
+# Assume that your command is `demucs --mp3 --two-stems vocals -n mdx_extra "track with space.mp3"`
+# The following codes are same as the command above:
+import demucs.separate
+demucs.separate.main(["--mp3", "--two-stems", "vocals", "-n", "mdx_extra", "track with space.mp3"])
+
+# Or like this
+import demucs.separate
+import shlex
+demucs.separate.main(shlex.split('--mp3 --two-stems vocals -n mdx_extra "track with space.mp3"'))
+```
 
 ## Training Demucs
 

demucs/separate.py

@@ -49,7 +49,7 @@ def load_track(track, audio_channels, samplerate):
     return wav
 
 
-def main():
+def main(opts=None):
     parser = argparse.ArgumentParser("demucs.separate",
                                      description="Separate the sources for the given tracks")
     parser.add_argument("tracks", nargs='+', type=Path, default=[], help='Path to tracks')
@@ -115,7 +115,7 @@ def main():
                         help="Number of jobs. This can increase memory usage but will "
                              "be much faster when multiple cores are available.")
 
-    args = parser.parse_args()
+    args = parser.parse_args(opts)
 
     try:
         model = get_model_from_args(args)