Hugging Face's logo

niobures
/
Demucs

ONNX
Safetensors
Model card Files
xet
Community
niobures commited on
Commit
2d548ca
·
verified ·
1 Parent(s): dc3c48c

Demucs (models)

Browse files
Files changed (31) hide show
  1. .gitattributes +2 -0
  2. models/demucs-openvino/.gitattributes +35 -0
  3. models/demucs-openvino/README.md +43 -0
  4. models/demucs-openvino/htdemucs_v4/htdemucs_fwd.bin +3 -0
  5. models/demucs-openvino/htdemucs_v4/htdemucs_fwd.xml +0 -0
  6. models/demucs-openvino/htdemucs_v4_6s/htdemucs_fwd.bin +3 -0
  7. models/demucs-openvino/htdemucs_v4_6s/htdemucs_fwd.xml +0 -0
  8. models/demucs-openvino/htdemucs_v4_ht_bass/htdemucs_fwd.bin +3 -0
  9. models/demucs-openvino/htdemucs_v4_ht_bass/htdemucs_fwd.xml +0 -0
  10. models/demucs-openvino/htdemucs_v4_ht_drums/htdemucs_fwd.bin +3 -0
  11. models/demucs-openvino/htdemucs_v4_ht_drums/htdemucs_fwd.xml +0 -0
  12. models/demucs-openvino/htdemucs_v4_ht_other/htdemucs_fwd.bin +3 -0
  13. models/demucs-openvino/htdemucs_v4_ht_other/htdemucs_fwd.xml +0 -0
  14. models/demucs-openvino/htdemucs_v4_ht_vocals/htdemucs_fwd.bin +3 -0
  15. models/demucs-openvino/htdemucs_v4_ht_vocals/htdemucs_fwd.xml +0 -0
  16. models/demucs-openvino/source.txt +1 -0
  17. models/demucs_denoiser/.gitattributes +34 -0
  18. models/demucs_denoiser/README.md +4 -0
  19. models/demucs_denoiser/metadata.json +1 -0
  20. models/demucs_denoiser/model.pt +3 -0
  21. models/demucs_denoiser/source.txt +1 -0
  22. models/demucs_extra/.gitattributes +27 -0
  23. models/demucs_extra/README.md +16 -0
  24. models/demucs_extra/metadata.json +1 -0
  25. models/demucs_extra/model.pt +3 -0
  26. models/demucs_extra/source.txt +1 -0
  27. models/demucs_v3_saxophone_separation/.gitattributes +36 -0
  28. models/demucs_v3_saxophone_separation/README.md +41 -0
  29. models/demucs_v3_saxophone_separation/Reconstructing the Charlie Parker Omnibook using an audio-to-score automatic transcription pipeline.pdf +3 -0
  30. models/demucs_v3_saxophone_separation/filosax_demucs_v3_14.22_SDR.th +3 -0
  31. models/demucs_v3_saxophone_separation/source.txt +1 -0
.gitattributes CHANGED
@@ -84,3 +84,5 @@ models/htdemucs_ft/92cfc3b6-ef3bcb9c.th filter=lfs diff=lfs merge=lfs -text
84
  models/htdemucs_ft/d12395a8-e57c48e6.th filter=lfs diff=lfs merge=lfs -text
85
  models/htdemucs_ft/f7e0c4bc-ba3fe64a.th filter=lfs diff=lfs merge=lfs -text
86
  models/htdemucs-ort/htdemucs.ort filter=lfs diff=lfs merge=lfs -text
 
 
 
84
  models/htdemucs_ft/d12395a8-e57c48e6.th filter=lfs diff=lfs merge=lfs -text
85
  models/htdemucs_ft/f7e0c4bc-ba3fe64a.th filter=lfs diff=lfs merge=lfs -text
86
  models/htdemucs-ort/htdemucs.ort filter=lfs diff=lfs merge=lfs -text
87
+ models/demucs_v3_saxophone_separation/filosax_demucs_v3_14.22_SDR.th filter=lfs diff=lfs merge=lfs -text
88
+ models/demucs_v3_saxophone_separation/Reconstructing[[:space:]]the[[:space:]]Charlie[[:space:]]Parker[[:space:]]Omnibook[[:space:]]using[[:space:]]an[[:space:]]audio-to-score[[:space:]]automatic[[:space:]]transcription[[:space:]]pipeline.pdf filter=lfs diff=lfs merge=lfs -text
models/demucs-openvino/.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
models/demucs-openvino/README.md ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ ---
4
+
5
+ # Demucs OpenVINO
6
+
7
+ This repo stores OpenVINO(TM) models in IR format that are used to perform Music Separation.
8
+
9
+ Currently, the models stored here (htdemucs_fwd.xml, htdemucs_fwd.bin) is a conversion of the Demucs v4 model, with some 'outer' operations (such as stft, istft) stripped out.
10
+
11
+ This model stores the model conversions for the following six configurations:
12
+ * HTDemucs v4
13
+ * HTDemucs FT (fine-tuned) Bass
14
+ * HTDemucs FT (fine-tuned) Drums
15
+ * HTDemucs FT (fine-tuned) Other
16
+ * HTDemucs FT (fine-tuned) Vocals
17
+ * HTDemucs v4 6S (6-Stem)
18
+
19
+ This is intended to be used with the set of OpenVINO-based AI plugins for Audacity(R), here: https://github.com/intel/openvino-plugins-ai-audacity
20
+
21
+ More specifically, see details of pure-C++ implementation of the htdemucs pipeline here: https://github.com/intel/openvino-plugins-ai-audacity/blob/main/mod-openvino/htdemucs.cpp
22
+
23
+ This pipeline was ported from htdemucs.py, found here: https://github.com/facebookresearch/demucs
24
+
25
+ # Citations:
26
+ ```
27
+ @inproceedings{rouard2022hybrid,
28
+ title={Hybrid Transformers for Music Source Separation},
29
+ author={Rouard, Simon and Massa, Francisco and D{\'e}fossez, Alexandre},
30
+ booktitle={ICASSP 23},
31
+ year={2023}
32
+ }
33
+
34
+ @inproceedings{defossez2021hybrid,
35
+ title={Hybrid Spectrogram and Waveform Source Separation},
36
+ author={D{\'e}fossez, Alexandre},
37
+ booktitle={Proceedings of the ISMIR 2021 Workshop on Music Source Separation},
38
+ year={2021}
39
+ }
40
+ ```
41
+
42
+ ## Intel’s Human Rights Disclaimer:
43
+ Intel is committed to respecting human rights and avoiding complicity in human rights abuses. See Intel's Global Human Rights Principles. Intel's products and software are intended only to be used in applications that do not cause or contribute to a violation of an internationally recognized human right.
models/demucs-openvino/htdemucs_v4/htdemucs_fwd.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74c4e1ebd68b648ea5a2aabefb65d5c3ba805658037fc97a37b84ce9c72f4eb1
3
+ size 104552746
models/demucs-openvino/htdemucs_v4/htdemucs_fwd.xml ADDED
The diff for this file is too large to render. See raw diff
 
models/demucs-openvino/htdemucs_v4_6s/htdemucs_fwd.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d66281099b5fdaba8844e306f3d6710b3e0b005fa9aad4514ce7604e24fbec9
3
+ size 74384618
models/demucs-openvino/htdemucs_v4_6s/htdemucs_fwd.xml ADDED
The diff for this file is too large to render. See raw diff
 
models/demucs-openvino/htdemucs_v4_ht_bass/htdemucs_fwd.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7ec34d838b0f8f36b11a90d6f4e588141a383faadc77e9648e19fdd9eefc95e
3
+ size 104552746
models/demucs-openvino/htdemucs_v4_ht_bass/htdemucs_fwd.xml ADDED
The diff for this file is too large to render. See raw diff
 
models/demucs-openvino/htdemucs_v4_ht_drums/htdemucs_fwd.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:340e5f6d8dd4d5d0d987f545b922a8252cc5ea6e53649f91eadd8b36e77fcbac
3
+ size 104552746
models/demucs-openvino/htdemucs_v4_ht_drums/htdemucs_fwd.xml ADDED
The diff for this file is too large to render. See raw diff
 
models/demucs-openvino/htdemucs_v4_ht_other/htdemucs_fwd.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5f4bb99e91fea0bda75f64086712884457a5c9f861d1c2a7a02e09e92c2846e
3
+ size 104552746
models/demucs-openvino/htdemucs_v4_ht_other/htdemucs_fwd.xml ADDED
The diff for this file is too large to render. See raw diff
 
models/demucs-openvino/htdemucs_v4_ht_vocals/htdemucs_fwd.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8576b4bd27095bc7f2dae39c529124b04eebc3e04009a45b7cc170f5b563f749
3
+ size 104552746
models/demucs-openvino/htdemucs_v4_ht_vocals/htdemucs_fwd.xml ADDED
The diff for this file is too large to render. See raw diff
 
models/demucs-openvino/source.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ https://huggingface.co/Intel/demucs-openvino
models/demucs_denoiser/.gitattributes ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tflite filter=lfs diff=lfs merge=lfs -text
29
+ *.tgz filter=lfs diff=lfs merge=lfs -text
30
+ *.wasm filter=lfs diff=lfs merge=lfs -text
31
+ *.xz filter=lfs diff=lfs merge=lfs -text
32
+ *.zip filter=lfs diff=lfs merge=lfs -text
33
+ *.zst filter=lfs diff=lfs merge=lfs -text
34
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
models/demucs_denoiser/README.md ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - audacity
4
+ ---
models/demucs_denoiser/metadata.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"sample_rate": 16000, "domain_tags": ["environmental"], "short_description": "demucs pretrained", "long_description": "demucs pretrained", "tags": ["denoising"], "labels": ["mono"], "effect_type": "waveform-to-waveform", "multichannel": false}
models/demucs_denoiser/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec19e077c0849d368b3ba6cc497bb6dacd579ab58d97cf9d9040b436559d181b
3
+ size 137439769
models/demucs_denoiser/source.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ https://huggingface.co/davidwmcdevitt/demucs_denoiser
models/demucs_extra/.gitattributes ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bin.* filter=lfs diff=lfs merge=lfs -text
5
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.model filter=lfs diff=lfs merge=lfs -text
12
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
13
+ *.onnx filter=lfs diff=lfs merge=lfs -text
14
+ *.ot filter=lfs diff=lfs merge=lfs -text
15
+ *.parquet filter=lfs diff=lfs merge=lfs -text
16
+ *.pb filter=lfs diff=lfs merge=lfs -text
17
+ *.pt filter=lfs diff=lfs merge=lfs -text
18
+ *.pth filter=lfs diff=lfs merge=lfs -text
19
+ *.rar filter=lfs diff=lfs merge=lfs -text
20
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
21
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
22
+ *.tflite filter=lfs diff=lfs merge=lfs -text
23
+ *.tgz filter=lfs diff=lfs merge=lfs -text
24
+ *.xz filter=lfs diff=lfs merge=lfs -text
25
+ *.zip filter=lfs diff=lfs merge=lfs -text
26
+ *.zstandard filter=lfs diff=lfs merge=lfs -text
27
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
models/demucs_extra/README.md ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags: audacity
3
+ ---
4
+
5
+ ## Music Source Separation in the Waveform Domain
6
+
7
+ This is the Demucs model, serialized from Facebook Research's pretrained models.
8
+
9
+ From Facebook research:
10
+
11
+ Demucs is based on U-Net convolutional architecture inspired by Wave-U-Net and SING, with GLUs, a BiLSTM between the encoder and decoder, specific initialization of weights and transposed convolutions in the decoder.
12
+
13
+
14
+ This is the `demucs_extra` version, meaning that is was trained on the MusDB dataset, along with 150 extra songs of data.
15
+
16
+ See [facebookresearch's repository](https://github.com/facebookresearch/demucs) for more information on Demucs.
models/demucs_extra/metadata.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"sample_rate": 44100, "domain_tags": ["music"], "short_description": "Use me for separating into Drums, Bass, Vocals, and Other!", "long_description": "This is the Demucs model (demucs_extra), serialized from facebookresearch's repository.", "tags": ["music", "musdb"], "labels": ["drums", "bass", "other", "vocals"], "effect_type": "waveform-to-waveform", "multichannel": false}
models/demucs_extra/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd909d118fcf78d7c39993072da1f5c3a39b8d3c24636b4528d870b9299aada9
3
+ size 1062834890
models/demucs_extra/source.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ https://huggingface.co/hugggof/demucs_extra
models/demucs_v3_saxophone_separation/.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ filosax_demucs_v3_14.22_SDR.th filter=lfs diff=lfs merge=lfs -text
models/demucs_v3_saxophone_separation/README.md ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - saxophone
5
+ - tenor
6
+ - alto
7
+ - baritone
8
+ - demucs
9
+ ---
10
+ # Saxophone Source Separation model
11
+
12
+ - paper: [https://arxiv.org/abs/2405.16687](https://arxiv.org/abs/2405.16687)
13
+
14
+ Source separation model trained for the paper:
15
+
16
+ > Reconstructing the Charlie Parker Omnibook using an audio-to-score automatic transcription pipeline
17
+ > Xavier Riley and Simon Dixon
18
+ > SMC 2024, Porto, Portugal
19
+
20
+ Separates tenor sax cleanly but struggles a little with high register playing.
21
+
22
+ ## Dependencies
23
+
24
+ ```
25
+ pip install demucs==3.0.6
26
+ ```
27
+
28
+ ## Usage
29
+
30
+ ```
31
+ python -mdemucs --repo . -n filosax_demucs_v3_14.22_SDR.th -o . input.wav
32
+ ```
33
+
34
+ ## Alternative
35
+
36
+ For an alternative you could also check out the UVR Wind model
37
+
38
+ ```
39
+ pip install audio-separator[gpu] # or leave off [gpu] if you only have CPU
40
+ audio-separator -m 17_HP-Wind_Inst-UVR.pth input.wav
41
+ ```
models/demucs_v3_saxophone_separation/Reconstructing the Charlie Parker Omnibook using an audio-to-score automatic transcription pipeline.pdf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e74e939573dbd440fd28078e2cee9d7e918d434c778f380460bbedda1caf897
3
+ size 423064
models/demucs_v3_saxophone_separation/filosax_demucs_v3_14.22_SDR.th ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a801bc00f0e21d476edef1d9fa25dbcb088e3bae0a4092e590167ae26dbe360
3
+ size 74553707
models/demucs_v3_saxophone_separation/source.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ https://huggingface.co/xavriley/demucs_v3_saxophone_separation