no-op-ul-se
commited on
Commit
•
5258730
1
Parent(s):
f8efefb
pluma, pond brain and franziska sax models
Browse files- README.md +52 -3
- birds_pluma_b2048_r48000_z12.ts +3 -0
- humpbacks_pondbrain_b2048_r48000_z20.ts +3 -0
- marinemammals_pondbrain_b2048_r48000_z20.ts +3 -0
- organ_bach_b2048_sr48000_z16.ts → organ_bach_b2048_r48000_z16.ts +0 -0
- sax_soprano_franziskaschroeder_b2048_r48000_z20.ts +3 -0
- water_pondbrain_b2048_r48000_z16.ts +3 -0
README.md
CHANGED
@@ -4,28 +4,39 @@ license: cc-by-nc-4.0
|
|
4 |
|
5 |
# RAVE Models
|
6 |
|
|
|
7 |
This is a collection of [RAVE](https://github.com/acids-ircam/RAVE) models trained by the [Intelligent Instruments Lab](https://iil.is) for various projects.
|
8 |
|
9 |
Most of these models are encoder-decoder only, no prior, and all use the `--causal` mode and are exported for streaming inference with [nn~](https://github.com/acids-ircam/nn_tilde), [NN.ar](https://github.com/elgiano/nn.ar) or [rave-supercollider](https://github.com/victor-shepardson/rave-supercollider).
|
10 |
|
|
|
|
|
11 |
### guitar_iil_b2048_r48000_z16.ts
|
12 |
|
13 |
-
Dataset: [IILGuitarTimbre](https://github.com/Intelligent-Instruments-Lab/IILGuitarTimbre).
|
14 |
|
15 |
Model: modified RAVE v1, 48kHz, block size 2048, 16 latent dimensions.
|
16 |
|
17 |
### organ_archive_b2048_r48000_z16.ts
|
18 |
|
19 |
-
Dataset:
|
20 |
|
21 |
Model: modified RAVE v1, 48kHz, block size 2048, 16 latent dimensions.
|
22 |
|
23 |
### organ_bach_b2048_sr48000_z16.ts
|
24 |
|
25 |
-
Dataset: various recordings of J.
|
26 |
|
27 |
Model: modified RAVE v1, 48kHz, block size 2048, 16 latent dimensions.
|
28 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
### voice_vocalset_b2048_r48000_z16.ts
|
30 |
|
31 |
Dataset: [VocalSet](https://zenodo.org/record/1193957) singing voice dataset.
|
@@ -50,5 +61,43 @@ Dataset: [CSTR VCTK Corpus](https://datashare.ed.ac.uk/handle/10283/3443) multis
|
|
50 |
|
51 |
Model: RAVE v3, 44.1kHz, block size 2048, 22 latent dimensions.
|
52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
53 |
|
54 |
|
|
|
4 |
|
5 |
# RAVE Models
|
6 |
|
7 |
+
|
8 |
This is a collection of [RAVE](https://github.com/acids-ircam/RAVE) models trained by the [Intelligent Instruments Lab](https://iil.is) for various projects.
|
9 |
|
10 |
Most of these models are encoder-decoder only, no prior, and all use the `--causal` mode and are exported for streaming inference with [nn~](https://github.com/acids-ircam/nn_tilde), [NN.ar](https://github.com/elgiano/nn.ar) or [rave-supercollider](https://github.com/victor-shepardson/rave-supercollider).
|
11 |
|
12 |
+
## Musical Instruments
|
13 |
+
|
14 |
### guitar_iil_b2048_r48000_z16.ts
|
15 |
|
16 |
+
Dataset: [IILGuitarTimbre](https://github.com/Intelligent-Instruments-Lab/IILGuitarTimbre), a timbre-oriented collection of plucking, strumming, striking scraping and more recorded dry from an electric guitar.
|
17 |
|
18 |
Model: modified RAVE v1, 48kHz, block size 2048, 16 latent dimensions.
|
19 |
|
20 |
### organ_archive_b2048_r48000_z16.ts
|
21 |
|
22 |
+
Dataset: various recordings of organ music sourced from archive.org. Small amounts of voice and other instruments were included, and vinyl record noises are prominent.
|
23 |
|
24 |
Model: modified RAVE v1, 48kHz, block size 2048, 16 latent dimensions.
|
25 |
|
26 |
### organ_bach_b2048_sr48000_z16.ts
|
27 |
|
28 |
+
Dataset: various recordings of J.S. Bach music for church organ.
|
29 |
|
30 |
Model: modified RAVE v1, 48kHz, block size 2048, 16 latent dimensions.
|
31 |
|
32 |
+
### sax_soprano_franziskaschroeder_b2048_r48000_z20.ts
|
33 |
+
|
34 |
+
Dataset: Soprano sax improvisation by [Franziska Schroeder](https://improvisationai.wordpress.com/).
|
35 |
+
|
36 |
+
Model: modified RAVE v1, 48kHz, block size 2048, 20 latent dimensions.
|
37 |
+
|
38 |
+
## Voice
|
39 |
+
|
40 |
### voice_vocalset_b2048_r48000_z16.ts
|
41 |
|
42 |
Dataset: [VocalSet](https://zenodo.org/record/1193957) singing voice dataset.
|
|
|
61 |
|
62 |
Model: RAVE v3, 44.1kHz, block size 2048, 22 latent dimensions.
|
63 |
|
64 |
+
## *Pluma* Birds
|
65 |
+
|
66 |
+
This model of bird sounds was curated by Giacomo Lepri for his instrument *[Pluma](http://www.giacomolepri.com/pluma)*
|
67 |
+
|
68 |
+
### birds_pluma_b2048_r48000_z12.ts
|
69 |
+
|
70 |
+
Dataset: bird sounds.
|
71 |
+
|
72 |
+
Model: modified RAVE v1, 48kHz, block size 2048, 12 latent dimensions.
|
73 |
+
|
74 |
+
## *Pond Brain* Marine Sounds
|
75 |
+
|
76 |
+
These models of marine sounds were trained for [Jenna Sutela](https://jennasutela.com/)'s *Pond Brain* installations at [Copenhagen Contemporary](https://copenhagencontemporary.org/en/yet-it-moves-read-online/) and the [Helsinki Biennial](https://helsinkibiennaali.fi/en/artist/jenna-sutela/)
|
77 |
+
|
78 |
+
### water_pondbrain_b2048_r48000_z16.ts
|
79 |
+
|
80 |
+
Dataset: water recordings from freesound.org.
|
81 |
+
<details>
|
82 |
+
<summary>list of freesound users</summary>
|
83 |
+
`inspectorj`, `inchadney`, `aesqe`, `vonfleisch`, `javetakami`, `atomediadesign`, `kolezan`, `zabuhailo`, `zaziesound`, `repdac3`, `al_sub`, `lgarrett`, `uzbazur`, `lydmakeren`, `frenkfurth`, `edo333`, `boredtoinsanity`, `owl`, `kaydinhamby`, `tliedes`, `ilmari_freesound`, `manoslindos`, `l3ardoc`, `alexbuk`, `s-light`
|
84 |
+
</details>
|
85 |
+
|
86 |
+
Model: modified RAVE v1, 48kHz, block size 2048, 16 latent dimensions.
|
87 |
+
|
88 |
+
### humpbacks_pondbrain_b2048_r48000_z20.ts
|
89 |
+
|
90 |
+
Dataset: humpback whale recordings from the [Watkins database](https://cis.whoi.edu/science/B/whalesounds/index.cfm), [MBARI](https://freesound.org/people/MBARI_MARS/), and BBC.
|
91 |
+
|
92 |
+
Model: modified RAVE v1, 48kHz, block size 2048, 20 latent dimensions.
|
93 |
+
|
94 |
+
### marinemammals_pondbrain_b2048_r48000_z20.ts
|
95 |
+
|
96 |
+
Dataset: various marine mammal sounds from [NOAA](https://www.fisheries.noaa.gov/national/science-data/sounds-ocean-mammals), the [Watkins database](https://cis.whoi.edu/science/B/whalesounds/index.cfm), freesound users `felixblume` and `geraldfiebig`, and sound effects databases.
|
97 |
+
|
98 |
+
Model: modified RAVE v1, 48kHz, block size 2048, 20 latent dimensions.
|
99 |
+
|
100 |
+
|
101 |
+
|
102 |
|
103 |
|
birds_pluma_b2048_r48000_z12.ts
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a12ad61a2b0b5ee2329a72993bd94386a571600b37dd23feaa0a404940468d68
|
3 |
+
size 42105901
|
humpbacks_pondbrain_b2048_r48000_z20.ts
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81541b32ff2762ca7f7dd5729aa43a928e2d134c3a76aca335dee2bd7ffc09eb
|
3 |
+
size 121408124
|
marinemammals_pondbrain_b2048_r48000_z20.ts
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1710653e87e7ec8ca546a59139aa26b99a745ae3347abd4843bffee77dc50d70
|
3 |
+
size 121407190
|
organ_bach_b2048_sr48000_z16.ts → organ_bach_b2048_r48000_z16.ts
RENAMED
File without changes
|
sax_soprano_franziskaschroeder_b2048_r48000_z20.ts
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:216cf07fe8c121671b23771b03652c23fa39a20f7e7072d093cce1aef3fda3ae
|
3 |
+
size 121405924
|
water_pondbrain_b2048_r48000_z16.ts
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90908881f71faff5eb842a367078818cf68c8f39cd733699e08ffc2f765de658
|
3 |
+
size 121406128
|