Richard Zhu commited on
Commit
8b30617
Β·
1 Parent(s): d4afb7f

fix folder structure

Browse files
chord_harp/Dockerfile β†’ Dockerfile RENAMED
File without changes
chord_harp/app.py β†’ app.py RENAMED
File without changes
chord_harp/.DS_Store DELETED
Binary file (8.2 kB)
 
chord_harp/ChordEstimation DELETED
@@ -1 +0,0 @@
1
- Subproject commit bdd05b2236130f01ca2875a30297f3f368fbf470
 
 
chord_harp/ChordRecognitionMIDITrainedExtractor DELETED
@@ -1 +0,0 @@
1
- Subproject commit 19b81f694dae7782111b1be0e39e66f42fa1615f
 
 
chord_harp/README.md DELETED
@@ -1,21 +0,0 @@
1
- ---
2
- title: Automatic Chord Recognition
3
- emoji: 🎡
4
- colorFrom: blue
5
- colorTo: purple
6
- sdk: docker
7
- app_port: 7860
8
- ---
9
-
10
- # Automatic Chord Recognition (PyHARP)
11
-
12
- This is a [PyHARP](https://github.com/TEAMuP-dev/pyharp) app that estimates chord progressions from audio using the model proposed in:
13
-
14
- > Wu, Y., & Li, W. (2019). Automatic Audio Chord Recognition With MIDI-Trained Deep Feature and BLSTM-CRF Sequence Decoding Model. *IEEE/ACM Transactions on Audio, Speech, and Language Processing*, 27(2), 355–366.
15
-
16
- ## How it works
17
- 1. Upload an audio file in HARP
18
- 2. The model extracts a Harmonic CQT spectrogram
19
- 3. A CNN extracts pitch class features (trained on MIDI data)
20
- 4. A BLSTM-CRF decodes the chord label sequence
21
- 5. Time-stamped chord labels are returned and displayed in HARP
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
chord_harp/packages.txt β†’ packages.txt RENAMED
File without changes
chord_harp/patch_madmom.py β†’ patch_madmom.py RENAMED
File without changes
chord_harp/requirements.txt β†’ requirements.txt RENAMED
File without changes