Final doc updates for v0.3.0 (#96)

* add separation and new data_home * fixes in docs * minor improvements * add sep readme * fix sep readme
MTG · Nov 5, 2023 · df22133 · df22133
1 parent d96f880
commit df22133
Show file tree

Hide file tree

Showing 10 changed files with 48 additions and 26 deletions.
diff --git a/compiam/separation/README.md b/compiam/separation/README.md
@@ -0,0 +1,8 @@
+# Source separation tools
+
+| **Tool**                  | **Task**                         | **Paper** |
+|---------------------------|----------------------------------|-----------|
+| ColdDiffSep               | Singing voice extraction         | [1]       |
+
+
+[1] G. Plaja-Roglans, M. Miron, A. Shankar, and X. Serra, "Carnatic Singing Voice Separation using Cold Diffusion on Training Data with Bleeding", in International Society for Music Information Retrieval Conference (ISMIR 23), 2023. 
diff --git a/docs/index.rst b/docs/index.rst
@@ -48,12 +48,12 @@ If you use compIAM for your research, please consider citing our work as:
 
 .. code-block:: bibtex
 
-    @software{compiam_mtg_2022,
+    @software{compiam_mtg,
         author = {{Genís Plaja-Roglans and Thomas Nuttall and Xavier Serra}},
         title = {compIAM},
         url = {https://mtg.github.io/compIAM/},
-        version = {0.1.0},
-        year = {2022}
+        version = {0.3.0},
+        year = {2023}
     }
 
 
@@ -71,6 +71,7 @@ If you use compIAM for your research, please consider citing our work as:
    source/rhythm
    source/structure
    source/timbre
+   source/separation
 
 .. toctree::
    :caption: Datasets

diff --git a/docs/source/basic_usage.rst b/docs/source/basic_usage.rst
@@ -9,7 +9,7 @@ your Python project with: ``import compiam``.
 
 The integrated tools and models are organized by:
 
-#. First, the following fundamental musical aspects: melody, rhythm, structure and timbre. 
+#. First, the following fundamental musical aspects: melody, rhythm, structure, timbre, and from v0.3.0 we have included separation as well.
 #. Then, the tools are grouped by tasks.
 
 You can access the several included tools by importing them from their corresponding modules:
@@ -53,4 +53,8 @@ compIAM also includes wrappers to easily initialize relevant datasets, corpora,
 Model weights are large in size and therefore, not included in the library from v0.2.1 on. We have included a ``.download_model()``
 function to all ML/DL models that require pre-trained weights, so that the user can download them on demand. This function is
 automatically run when invoking the model through the ``compiam.load_model()`` wrapper. The model weights are then stored in the
-corresponding default folder ``./compiam/model/``. If the model is already downloaded, the function will not download it again.
+corresponding default folder ``./compiam/model/``. If the model is already downloaded, the function will not download it again.
+
+.. note::
+    From v0.3.0 on, ``compiam.load_model()`` wrapper has an argument ``data_home``, in where you can specify to which folder you
+    want the models to be downloaded and read from.
diff --git a/docs/source/contributing.rst b/docs/source/contributing.rst
@@ -157,7 +157,7 @@ Development step 4: creating a pull request (PR)
 Post-development
 ----------------
 
-Cool :) Your tool is now merged in compiam, and will be published in ``pypi`` in the next release.
+Cool!! Your tool is now merged in compiam, and will be published in ``pypi`` in the next release.
 Make sure you also take advantage of this feature, spread the word, and please keep being part of the compiam community. 
 
 Some future PRs might involve your tool (change of inner structure of the library, updating dependencies, etc…).

diff --git a/docs/source/melody.rst b/docs/source/melody.rst
@@ -34,16 +34,9 @@ FTANet-Carnatic
 .. note::
     REQUIRES: tensorflow
 
-.. automodule:: compiam.melody.pitch_extraction.ftanet_carnatic
+.. automodule:: compiam.melody.pitch_extraction.ftanet_carnatic.*
    :members:
 
-FTANet-Carnatic utils
-^^^^^^^^^^^^^^^^^^^^^
-
-.. automodule:: compiam.melody.pitch_extraction.ftanet_carnatic.pitch_processing
-   :members:
-
-
 Melodic Pattern Discovery
 +++++++++++++++++++++++++
 
@@ -53,7 +46,7 @@ Sancara search
 .. note::
     REQUIRES: torch
 
-.. automodule:: compiam.melody.pattern.sancara_search
+.. automodule:: compiam.melody.pattern.sancara_search.*
    :members:
 
 CAE-Carnatic (Wrapper)
@@ -62,7 +55,7 @@ CAE-Carnatic (Wrapper)
 .. note::
     REQUIRES: torch
 
-.. automodule:: compiam.melody.pattern.sancara_search.complex_auto
+.. automodule:: compiam.melody.pattern.sancara_search.complex_auto.*
    :members:
 
 Self-similarity matrix
@@ -71,7 +64,7 @@ Self-similarity matrix
 .. note::
     REQUIRES: torch
 
-.. automodule:: compiam.melody.pattern.sancara_search.extraction
+.. automodule:: compiam.melody.pattern.sancara_search.extraction.*
    :members:
 
 
@@ -84,12 +77,12 @@ DEEPSRGM
 .. note::
     REQUIRES: torch
 
-.. automodule:: compiam.melody.raga_recognition.deepsrgm
+.. automodule:: compiam.melody.raga_recognition.deepsrgm.*
    :members:
 
 DEEPSRGM utils
 ^^^^^^^^^^^^^^
 
-.. automodule:: compiam.melody.raga_recognition.deepsrgm.model
+.. automodule:: compiam.melody.raga_recognition.deepsrgm.model.*
    :members:
 
diff --git a/docs/source/rhythm.rst b/docs/source/rhythm.rst
@@ -13,7 +13,7 @@ Mnemonic Transcription
 .. note::
     REQUIRES: torch
 
-.. automodule:: compiam.rhythm.transcription.mnemonic_transcription
+.. automodule:: compiam.rhythm.transcription.mnemonic_transcription.*
    :members:
 
 
@@ -23,5 +23,5 @@ Meter tracking
 Akshara Pulse Tracker
 ---------------------
 
-.. automodule:: compiam.rhythm.meter.akshara_pulse_tracker
+.. automodule:: compiam.rhythm.meter.akshara_pulse_tracker.*
    :members:
diff --git a/docs/source/separation.rst b/docs/source/separation.rst
@@ -0,0 +1,16 @@
+.. _separation:
+
+Separation
+==========
+
+Singing voice extraction
+++++++++++++++++++++++++
+
+Leakage-aware Carnatic Singing Voice Separation
+-----------------------------------------------
+
+.. note::
+    REQUIRES: tensorflow
+
+.. automodule:: compiam.separation.singing_voice_extraction.cold_diff_sep.*
+   :members:
diff --git a/docs/source/structure.rst b/docs/source/structure.rst
@@ -12,6 +12,6 @@ Dhrupad Bandish Segmentation
 .. note::
     REQUIRES: torch
 
-.. automodule:: compiam.structure.segmentation.dhrupad_bandish_segmentation
+.. automodule:: compiam.structure.segmentation.dhrupad_bandish_segmentation.*
    :members:
    :inherited-members:
diff --git a/docs/source/timbre.rst b/docs/source/timbre.rst
@@ -12,6 +12,6 @@ Mridangam Stroke Classification
 .. note::
     REQUIRES: essentia
 
-.. automodule:: compiam.timbre.stroke_classification.mridangam_stroke_classification
+.. automodule:: compiam.timbre.stroke_classification.mridangam_stroke_classification.*
    :members:
    :inherited-members:
diff --git a/docs/source/visualisation.rst b/docs/source/visualisation.rst
@@ -4,17 +4,17 @@ Visualisation tools
 PyPeaks for Indian Art Music
 ++++++++++++++++++++++++++++
 
-.. automodule:: compiam.visualisation.peaks.data
+.. automodule:: compiam.visualisation.peaks.*
    :members:
 
 Audio visualisation utils
 ++++++++++++++++++++++++++
 
-.. automodule:: compiam.visualisation.audio
+.. automodule:: compiam.visualisation.audio.*
    :members:
 
 Training visualisation utils
 ++++++++++++++++++++++++++++
 
-.. automodule:: compiam.visualisation.training
+.. automodule:: compiam.visualisation.training.*
    :members: