Updated github actions workflows

.github/workflows/ci.yml

@@ -47,7 +47,7 @@ jobs:
                       envfile: ".github/environment-ci.yml"
 
         steps:
-        - uses: actions/checkout@v3
+        - uses: actions/checkout@v4
           with:
             submodules: true
 
@@ -65,7 +65,7 @@ jobs:
             esac
 
         - name: Cache conda
-          uses: actions/cache@v3
+          uses: actions/cache@v4
           env:
             CACHE_NUMBER: 2      
           with:
@@ -77,7 +77,7 @@ jobs:
               ${{ runner.os }}-conda-
 
         - name: Setup conda
-          uses: conda-incubator/setup-miniconda@v2
+          uses: conda-incubator/setup-miniconda@v3
           with:
             miniforge-variant: Miniforge3  
             miniforge-version: latest

.github/workflows/formatting.yml

@@ -12,7 +12,7 @@ jobs:
   black:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - name: black on mirdata
         uses: psf/black@stable
         with:

.github/workflows/lint-python.yml

@@ -21,18 +21,18 @@ jobs:
             channel-priority: "flexible"
             envfile: ".github/environment-lint.yml"
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
       with:
         fetch-depth: 0
     - name: Cache conda
-      uses: actions/cache@v3
+      uses: actions/cache@v4
       env:
         CACHE_NUMBER: 0
       with:
         path: ~/conda_pkgs_dir
         key: ${{ runner.os }}-${{ matrix.python-version }}-conda-${{ env.CACHE_NUMBER }}-${{ hashFiles( matrix.envfile ) }}
     - name: Install conda environmnent
-      uses: conda-incubator/setup-miniconda@v2
+      uses: conda-incubator/setup-miniconda@v3
       with: 
         auto-update-conda: true
         python-version: ${{ matrix.python-version }}

mirdata/annotations.py

@@ -1,5 +1,4 @@
-"""mirdata annotation data types
-"""
+"""mirdata annotation data types"""
 
 import logging
 import re

mirdata/core.py

@@ -1,5 +1,4 @@
-"""Core mirdata classes
-"""
+"""Core mirdata classes"""
 
 import json
 import os

mirdata/datasets/acousticbrainz_genre.py

@@ -16,10 +16,10 @@
 
     We provide four datasets containing genre and subgenre annotations extracted from four different online metadata sources:
 
-    - AllMusic and Discogs are based on editorial metadata databases maintained by music experts and enthusiasts. These sources 
-      contain explicit genre/subgenre annotations of music releases (albums) following a predefined genre namespace and taxonomy. 
+    - AllMusic and Discogs are based on editorial metadata databases maintained by music experts and enthusiasts. These sources
+      contain explicit genre/subgenre annotations of music releases (albums) following a predefined genre namespace and taxonomy.
       We propagated release-level annotations to recordings (tracks) in AcousticBrainz to build the datasets.
-    - Lastfm and Tagtraum are based on collaborative music tagging platforms with large amounts of genre labels provided by their 
+    - Lastfm and Tagtraum are based on collaborative music tagging platforms with large amounts of genre labels provided by their
       users for music recordings (tracks). We have automatically inferred a genre/subgenre taxonomy and annotations from these labels.
 
     For details on format and contents, please refer to the data webpage.
@@ -34,7 +34,7 @@
         The AcousticBrainz Genre Dataset: Multi-Source, Multi-Level, Multi-Label, and Large-Scale.
         20th International Society for Music Information Retrieval Conference (ISMIR 2019).
 
-    This work is partially supported by the European Union’s Horizon 2020 research and innovation programme under 
+    This work is partially supported by the European Union’s Horizon 2020 research and innovation programme under
     grant agreement No 688382 AudioCommons.
 
 """

mirdata/datasets/ballroom.py

@@ -24,11 +24,11 @@
     **Acknowledgments and References:**
 
     This dataset was created with the collaboration of experts in ballroom dance music. We extend our gratitude to those who contributed their knowledge and expertise to this project. For detailed information on the dataset and its creation, please refer to the associated research papers and documentation.
-    
+
     [1] Gouyon F., A. Klapuri, S. Dixon, M. Alonso, G. Tzanetakis, C. Uhle, and P. Cano. An experimental comparison of audio tempo induction algorithms. Transactions on Audio, Speech and Language Processing 14(5), pp.1832-1844, 2006.
 
     [2] Böck, S., and M. Schedl. Enhanced beat tracking with context-aware neural networks. In Proceedings of the International Conference on Digital Audio Effects (DAFX), 2010.
-    
+
     [3] Dixon, S., F. Gouyon & G. Widmer. Towards Characterisation of Music via Rhythmic Patterns. In Proceedings of the 5th International Society for Music Information Retrieval Conference (ISMIR). 2004.
 """
 

mirdata/datasets/candombe.py

@@ -3,14 +3,14 @@
 .. admonition:: Dataset Info
     :class: dropdown
 
-    This is a dataset of Candombe recordings with annotated beats and downbeats, totaling over 2 hours of audio. 
-    It comprises 35 complete performances by renowned players, in groups of three to five drums. 
+    This is a dataset of Candombe recordings with annotated beats and downbeats, totaling over 2 hours of audio.
+    It comprises 35 complete performances by renowned players, in groups of three to five drums.
     Recording sessions were conducted in studio, in the context of musicological research over the past two decades.
     A total of 26 tambor players took part, belonging to different generations and representing all the important traditional Candombe styles.
-    The audio files are stereo with a sampling rate of 44.1 kHz and 16-bit precision. 
+    The audio files are stereo with a sampling rate of 44.1 kHz and 16-bit precision.
     The location of beats and downbeats was annotated by an expert, adding to more than 4700 downbeats.
 
-    The audio is provided as .flac files and the annotations as .csv files. 
+    The audio is provided as .flac files and the annotations as .csv files.
     The values in the first column of the csv file are the time instants of the beats.
     The numbers on the second column indicate both the bar number and the beat number within the bar.
     For instance, 1.1, 1.2, 1.3 and 1.4 are the four beats of the first bar. Hence, each label ending with .1 indicates a downbeat.

mirdata/datasets/cipi.py

@@ -5,17 +5,17 @@
 
     The "Can I Play It?" (CIPI) dataset is a specialized collection of 652 classical piano scores, provided in a
     machine-readable MusicXML format and accompanied by integer-based difficulty levels ranging from 1 to 9, as
-    verified by expert pianists. Then, it provides embeddings for fingering and expresiveness of the piece. Each 
+    verified by expert pianists. Then, it provides embeddings for fingering and expresiveness of the piece. Each
     recording has multiple scores corresponding to it. This dataset focuses exclusively on classical piano music,
     offering a rich resource for music researchers, educators, and students. Developed by the Music Technology Group
-    in Barcelona, by P. Ramoneda et al. 
+    in Barcelona, by P. Ramoneda et al.
 
     The CIPI dataset facilitates various applications such as the study of musical complexity, the selection of
     appropriately leveled pieces for students, and general research in music education. The dataset, alongside
     embeddings of multiple dimensions of difficulty, has been made publicly available to encourage ongoing innovation
     and collaboration within the music education and research communities.
 
-    The dataset has been published alongside a paper in Expert Systems with Applications Journal. 
+    The dataset has been published alongside a paper in Expert Systems with Applications Journal.
 
     The dataset is shared under a Creative Commons Attribution Non Commercial Share Alike 4.0 International License, but
     need to be requested. Please do request the dataset here: https://zenodo.org/records/8037327. The dataset can only

mirdata/datasets/compmusic_carnatic_rhythm.py

@@ -11,7 +11,7 @@
 
     The dataset contains the following data:
 
-    **AUDIO:** The pieces are chosen from the CompMusic Carnatic music collection. The pieces were chosen in four popular taalas of 
+    **AUDIO:** The pieces are chosen from the CompMusic Carnatic music collection. The pieces were chosen in four popular taalas of
     Carnatic music, which encompasses a majority of Carnatic music. The pieces were chosen include a mix of vocal and instrumental recordings,
     new and old recordings, and to span a wide variety of forms. All pieces have a percussion accompaniment, predominantly Mridangam. The
     excerpts are full length pieces or a part of the full length pieces. There are also several different pieces by the same artist (or release
@@ -27,9 +27,9 @@
     **METADATA:** For each excerpt, the taala of the piece, edupu (offset of the start of the piece, relative to the sama, measured in aksharas)
     of the composition, and the kalai (the cycle length scaling factor) are recorded. Each excerpt can be uniquely identified and located with the
     MBID of the recording, and the relative start and end times of the excerpt within the whole recording. A separate 5 digit taala based unique ID
-    is also provided for each excerpt as a double check. The artist, release, the lead instrument, and the raaga of the piece are additional 
+    is also provided for each excerpt as a double check. The artist, release, the lead instrument, and the raaga of the piece are additional
     editorial metadata obtained from the release. A flag indicates if the excerpt is a full piece or only a part of a full piece. There are optional
-    comments on audio quality and annotation specifics. 
+    comments on audio quality and annotation specifics.
 
     Possible uses of the dataset: Possible tasks where the dataset can be used include taala, sama and beat tracking, tempo estimation and tracking,
     taala recognition, rhythm based segmentation of musical audio, structural segmentation, audio to score/lyrics alignment, and rhythmic pattern

mirdata/datasets/compmusic_carnatic_varnam.py

@@ -28,7 +28,7 @@
     **Sections**
     The notation is given a single time per section, however, to align the svaras with the tala annotations, structure
     information is given. The structure is given in yaml format, specifying the order of the sections, and how many svaras
-    are sung per each tala tick. Broadly, there are just two only cases, 2 svaras per tick, and 4 svaras per tick. 
+    are sung per each tala tick. Broadly, there are just two only cases, 2 svaras per tick, and 4 svaras per tick.
     The structure information has been added in the 1.1 version of the dataset.
 
     **Possible uses of the dataset**

mirdata/datasets/compmusic_hindustani_rhythm.py

@@ -3,8 +3,8 @@
 .. admonition:: Dataset Info
     :class: dropdown
 
-    CompMusic Hindustani Rhythm Dataset is a rhythm annotated test corpus for automatic rhythm analysis tasks in Hindustani Music. 
-    The collection consists of audio excerpts from the CompMusic Hindustani research corpus, manually annotated time aligned markers 
+    CompMusic Hindustani Rhythm Dataset is a rhythm annotated test corpus for automatic rhythm analysis tasks in Hindustani Music.
+    The collection consists of audio excerpts from the CompMusic Hindustani research corpus, manually annotated time aligned markers
     indicating the progression through the taal cycle, and the associated taal related metadata. A brief description of the dataset
     is provided below.
 
@@ -19,9 +19,9 @@
     The pieces are stereo, 160 kbps, mp3 files sampled at 44.1 kHz. The audio is also available as wav files for experiments.
 
     **SAM, VIBHAAG AND THE MAATRAS:** The primary annotations are audio synchronized time-stamps indicating the different metrical positions in the taal cycle.
-    The sam and matras of the cycle are annotated. The annotations were created using Sonic Visualizer by tapping to music and manually correcting the taps. 
+    The sam and matras of the cycle are annotated. The annotations were created using Sonic Visualizer by tapping to music and manually correcting the taps.
     Each annotation has a time-stamp and an associated numeric label that indicates the position of the beat marker in the taala cycle. The annotations and the
-    associated metadata have been verified for correctness and completeness by a professional Hindustani musician and musicologist. The long thick lines show 
+    associated metadata have been verified for correctness and completeness by a professional Hindustani musician and musicologist. The long thick lines show
     vibhaag boundaries. The numerals indicate the matra number in cycle. In each case, the sam (the start of the cycle, analogous to the downbeat) are indicated
     using the numeral 1.
 

mirdata/datasets/compmusic_indian_tonic.py

@@ -5,17 +5,17 @@
 
     This loader includes a combination of six different datasets for the task of Indian Art Music tonic identification.
 
-    These datasets comprise audio excerpts and manually done annotations of the tonic pitch of the lead artist for each audio excerpt. 
-    Each excerpt is accompanied by its associated editorial metadata. These datasets can be used to develop and evaluate computational 
-    approaches for automatic tonic identification in Indian art music. These datasets have been used in several articles mentioned below. 
-    A majority of These datasets come from the CompMusic corpora of Indian art music, for which each recording is associated with a MBID. 
+    These datasets comprise audio excerpts and manually done annotations of the tonic pitch of the lead artist for each audio excerpt.
+    Each excerpt is accompanied by its associated editorial metadata. These datasets can be used to develop and evaluate computational
+    approaches for automatic tonic identification in Indian art music. These datasets have been used in several articles mentioned below.
+    A majority of These datasets come from the CompMusic corpora of Indian art music, for which each recording is associated with a MBID.
     Through the MBID other information can be obtained using the Dunya API.
 
 
-    These six datasets are used for for the task of tonic identification for Indian Art Music, and can be used for a comparative evaluation. 
-    To the best of our knowledge these are the largest datasets available for tonic identification for Indian art  music. These datases vary 
-    in terms of the audio quality, recording period (decade), the number of recordings for Carnatic, Hindustani, male and female singers and 
-    instrumental and vocal excerpts. 
+    These six datasets are used for for the task of tonic identification for Indian Art Music, and can be used for a comparative evaluation.
+    To the best of our knowledge these are the largest datasets available for tonic identification for Indian art  music. These datases vary
+    in terms of the audio quality, recording period (decade), the number of recordings for Carnatic, Hindustani, male and female singers and
+    instrumental and vocal excerpts.
 
     All the datasets (annotations) are version controlled. The audio files corresponding to these datsets are made available on request
     for only research purposes. See DOWNLOAD_INFO of this loader.
@@ -25,7 +25,7 @@
     .. code-block::
 
         'ID': {
-            'artist': <name of the lead artist if available>, 
+            'artist': <name of the lead artist if available>,
             'filepath': <relative path to the audio file>,
             'gender': <gender of the lead singer if available>,
             'mbid': <musicbrainz id when available>,
@@ -41,10 +41,10 @@
     these features may be easily computed following the instructions in the related paper. See BIBTEX.
 
     There are a total of 2161 audio excerpts, and while the CM collection includes aproximately 50% Carnatic and 50% Hindustani recordings, IITM and
-    IISc collections are 100% Carnatic music. The excerpts vary a lot in duration. See [this webpage](https://compmusic.upf.edu/iam-tonic-dataset) 
+    IISc collections are 100% Carnatic music. The excerpts vary a lot in duration. See [this webpage](https://compmusic.upf.edu/iam-tonic-dataset)
     for a detailed overview of the datasets.
 
-    If you have any questions or comments about the dataset, please feel free to email: [sankalp (dot) gulati (at) gmail (dot) com], or 
+    If you have any questions or comments about the dataset, please feel free to email: [sankalp (dot) gulati (at) gmail (dot) com], or
     [sankalp (dot) gulati (at) upf (dot) edu].
 
 """

mirdata/datasets/compmusic_raga.py

@@ -3,26 +3,26 @@
 .. admonition:: Dataset Info
     :class: dropdown
 
-    Rāga datasets from CompMusicomprise two sizable datasets, one for each music tradition, 
-    Carnatic and Hindustani. These datasets comprise full length audio recordings and their 
-    associated rāga labels. These two datasets can be used to develop and evaluate approaches 
+    Rāga datasets from CompMusicomprise two sizable datasets, one for each music tradition,
+    Carnatic and Hindustani. These datasets comprise full length audio recordings and their
+    associated rāga labels. These two datasets can be used to develop and evaluate approaches
     for performing automatic rāga recognition in Indian art music.
 
     These datasets are derived from the CompMusic corpora of Indian Art Music. Therefore, the
     dataset has been compiled at the Music Technology Group, by a group of researchers working
     on the computational analysis of Carnatic and Hindustani music within the framework of the
-    ERC-funded CompMusic project. 
-
-    Each recording is associated with a MBID. With the MBID other information can be obtained 
-    using the Dunya API or pycompmusic. 
+    ERC-funded CompMusic project.
 
-    The Carnatic subset comprises 124 hours of audio recordings and editorial metadata that 
-    includes carefully curated and verified rāga labels. It contains 480 recordings belonging 
+    Each recording is associated with a MBID. With the MBID other information can be obtained
+    using the Dunya API or pycompmusic.
+
+    The Carnatic subset comprises 124 hours of audio recordings and editorial metadata that
+    includes carefully curated and verified rāga labels. It contains 480 recordings belonging
     to 40 rāgas with 12 recordings per rāga.
 
-    The Hindustani subset comprises 116 hours of audio recordings and editorial metadata that 
-    includes carefully curated and verified rāga labels. It contains 300 recordings belonging 
-    to 30 rāgas with 10 recordings per rāga. 
+    The Hindustani subset comprises 116 hours of audio recordings and editorial metadata that
+    includes carefully curated and verified rāga labels. It contains 300 recordings belonging
+    to 30 rāgas with 10 recordings per rāga.
 
     The dataset also includes features per each file:
     * Tonic: float indicating the recording tonic
@@ -32,9 +32,9 @@
     * Nyas segments: KNN-extracted segments of Nyas (start and end times provided)
     * Tani segments: KNN-extracted segments of Tanis (start and end times provided)
 
-    The dataset includes both txt files and json files that contain information about each audio 
-    recording in terms of its mbid, the path of the audio/feature files and the associated rāga 
-    identifier. Each rāga is assigned a unique identifier by Dunya, which is similar to the mbid 
+    The dataset includes both txt files and json files that contain information about each audio
+    recording in terms of its mbid, the path of the audio/feature files and the associated rāga
+    identifier. Each rāga is assigned a unique identifier by Dunya, which is similar to the mbid
     in terms of purpose. A mapping of the rāga id to its transliterated name is also provided.
 
     For more information about the dataset please refer to: https://compmusic.upf.edu/node/328