ReDimNet (code, models, paper)
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +3 -0
- Reshape Dimensions Network for Speaker Recognition.pdf +3 -0
- code/paper_metrics.png +3 -0
- code/pretrained_models.png +3 -0
- code/redimnet.zip +3 -0
- code/releases/11.06.2024/M-vb2+vox2+cnc-ft_mix.pt +3 -0
- code/releases/11.06.2024/M-vb2-ptn.pt +3 -0
- code/releases/11.06.2024/S-vb2+vox2+cnc-ft_mix.pt +3 -0
- code/releases/11.06.2024/S-vb2-ptn.pt +3 -0
- code/releases/11.06.2024/b0-vox2-ft_lm.pt +3 -0
- code/releases/11.06.2024/b0-vox2-ptn.pt +3 -0
- code/releases/11.06.2024/b1-vox2-ft_lm.pt +3 -0
- code/releases/11.06.2024/b1-vox2-ptn.pt +3 -0
- code/releases/11.06.2024/b2-vox2-ft_lm.pt +3 -0
- code/releases/11.06.2024/b2-vox2-ptn.pt +3 -0
- code/releases/11.06.2024/b3-vox2-ft_lm.pt +3 -0
- code/releases/11.06.2024/b3-vox2-ptn.pt +3 -0
- code/releases/11.06.2024/b4-vox2-ft_lm.pt +3 -0
- code/releases/11.06.2024/b4-vox2-ptn.pt +3 -0
- code/releases/11.06.2024/b5-vox2-ft_lm.pt +3 -0
- code/releases/11.06.2024/b5-vox2-ptn.pt +3 -0
- code/releases/11.06.2024/b6-vox2-ft_lm.pt +3 -0
- code/releases/11.06.2024/b6-vox2-ptn.pt +3 -0
- code/releases/11.06.2024/redimnet-latest.zip +3 -0
- models/ReDimNet (voice-is-cool)/.gitattributes +35 -0
- models/ReDimNet (voice-is-cool)/M-vb2+vox2+cnc-ft_mix.pt +3 -0
- models/ReDimNet (voice-is-cool)/M-vb2-ptn.pt +3 -0
- models/ReDimNet (voice-is-cool)/README.md +3 -0
- models/ReDimNet (voice-is-cool)/S-vb2+vox2+cnc-ft_mix.pt +3 -0
- models/ReDimNet (voice-is-cool)/S-vb2-ptn.pt +3 -0
- models/ReDimNet (voice-is-cool)/b0-vox2-ft_lm.pt +3 -0
- models/ReDimNet (voice-is-cool)/b0-vox2-ptn.pt +3 -0
- models/ReDimNet (voice-is-cool)/b1-vox2-ft_lm.pt +3 -0
- models/ReDimNet (voice-is-cool)/b1-vox2-ptn.pt +3 -0
- models/ReDimNet (voice-is-cool)/b2-vox2-ft_lm.pt +3 -0
- models/ReDimNet (voice-is-cool)/b2-vox2-ptn.pt +3 -0
- models/ReDimNet (voice-is-cool)/b3-vox2-ft_lm.pt +3 -0
- models/ReDimNet (voice-is-cool)/b3-vox2-ptn.pt +3 -0
- models/ReDimNet (voice-is-cool)/b4-vox2-ft_lm.pt +3 -0
- models/ReDimNet (voice-is-cool)/b4-vox2-ptn.pt +3 -0
- models/ReDimNet (voice-is-cool)/b5-vox2-ft_lm.pt +3 -0
- models/ReDimNet (voice-is-cool)/b5-vox2-ptn.pt +3 -0
- models/ReDimNet (voice-is-cool)/b6-vox2-ft_lm.pt +3 -0
- models/ReDimNet (voice-is-cool)/b6-vox2-ptn.pt +3 -0
- models/ReDimNet (voice-is-cool)/source.txt +1 -0
- models/redimnet (wd929)/.gitattributes +35 -0
- models/redimnet (wd929)/README.md +5 -0
- models/redimnet (wd929)/redimnet_b6_sphereface2/config.yaml +94 -0
- models/redimnet (wd929)/redimnet_b6_sphereface2/models/model_115.pt +3 -0
- models/redimnet (wd929)/redimnet_b6_sphereface2/models/model_120.pt +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,6 @@ saved_model/**/* 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
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
code/paper_metrics.png filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
code/pretrained_models.png filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
Reshape[[:space:]]Dimensions[[:space:]]Network[[:space:]]for[[:space:]]Speaker[[:space:]]Recognition.pdf filter=lfs diff=lfs merge=lfs -text
|
Reshape Dimensions Network for Speaker Recognition.pdf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85dcf9a2959747058cad162acc29c2ab73a22a993b6d3f4cf4fa461b97b81226
|
| 3 |
+
size 1077477
|
code/paper_metrics.png
ADDED
|
Git LFS Details
|
code/pretrained_models.png
ADDED
|
Git LFS Details
|
code/redimnet.zip
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27c4ddf8c6edccfd4eb96043bb6e9c5016c7fb4f393774691f2b1280246145a0
|
| 3 |
+
size 1765554
|
code/releases/11.06.2024/M-vb2+vox2+cnc-ft_mix.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e0716c2f351e79df054554f17c525b899045d2d05e4c839208b975e87d94e6a
|
| 3 |
+
size 19726074
|
code/releases/11.06.2024/M-vb2-ptn.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42c13ce2bcf1ce466afdbe461c8dbe9471fc23204a1480fb4f306f48152f9af3
|
| 3 |
+
size 19714554
|
code/releases/11.06.2024/S-vb2+vox2+cnc-ft_mix.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76fa264eb8e0e07b143fb16b4eac5aa59ac480d63de4cd9691abf798cbe47fb3
|
| 3 |
+
size 13063610
|
code/releases/11.06.2024/S-vb2-ptn.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75dc73ad9088be38e55ea783820438b218d31e0171c2d50bdd8a950836cab5d1
|
| 3 |
+
size 13052090
|
code/releases/11.06.2024/b0-vox2-ft_lm.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68b8507be1f859d49e4cfd0c2d2bd7aa94e6a288a7df21e65276c9a5d5886cb0
|
| 3 |
+
size 4285894
|
code/releases/11.06.2024/b0-vox2-ptn.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7747c59fb22bc0e91f65a29465325fc26bfe889352d795c8099571d479e31b8e
|
| 3 |
+
size 4284704
|
code/releases/11.06.2024/b1-vox2-ft_lm.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e634bbbeb0f6afd9bbbb0606da834f93e23e4869b3954177a5717acc20ea36c
|
| 3 |
+
size 8730606
|
code/releases/11.06.2024/b1-vox2-ptn.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b20597cc5ee7eecd9ff57afe8c278dda3fc5a6d29e75e7ec780bf9dacc4da798
|
| 3 |
+
size 8729876
|
code/releases/11.06.2024/b2-vox2-ft_lm.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9b6bb2f6747caa28a41eaf2e372d66b0d1563baef186d18f5e99abd5e71e06f
|
| 3 |
+
size 20582650
|
code/releases/11.06.2024/b2-vox2-ptn.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c18a42926878bc8ac079623fbf36f0bc8054cda1199e96fbe1a3f8e131796647
|
| 3 |
+
size 20581530
|
code/releases/11.06.2024/b3-vox2-ft_lm.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4cf657265bb39464301c0f2db51c3f1014dca44959002560a48f8a6a4a3c4ad
|
| 3 |
+
size 13512475
|
code/releases/11.06.2024/b3-vox2-ptn.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3bd5bf57b7568a3e031bd761e2be02004423842768ec3ad3f6b857155c3ed8d
|
| 3 |
+
size 13509705
|
code/releases/11.06.2024/b4-vox2-ft_lm.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94d8c2e9f5234e7ec7cbc7b74dc773d4ba92f12768a4be61df2d571c2b4a9922
|
| 3 |
+
size 26301422
|
code/releases/11.06.2024/b4-vox2-ptn.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fa26daf3276f54509d170498caf119ac460f6268e7ce4a35e25ef1c7cb1c918
|
| 3 |
+
size 26299310
|
code/releases/11.06.2024/b5-vox2-ft_lm.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b0c11bbf5a3a8bb39e5c072c4192d0b694d8c447cf126d4cd3c7346a04b39c8
|
| 3 |
+
size 31174382
|
code/releases/11.06.2024/b5-vox2-ptn.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb8cc848c92c2a01fe225ee29daffbf3487b8183802a949c00986982755457cd
|
| 3 |
+
size 31172270
|
code/releases/11.06.2024/b6-vox2-ft_lm.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0f3034320c9cceaa8ed7c917a36e0affb501a922631d55c1007660eb1bbedea
|
| 3 |
+
size 60663214
|
code/releases/11.06.2024/b6-vox2-ptn.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b306026f7f469327d7a316105ab21d8d6ac3135d7eae1f5dd45c8ad656d251b2
|
| 3 |
+
size 60661102
|
code/releases/11.06.2024/redimnet-latest.zip
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b150979e615a0a4cc05dbe3f5bd1b4d06f9d3ba0558011cc120149b7462ea1ac
|
| 3 |
+
size 523193
|
models/ReDimNet (voice-is-cool)/.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/ReDimNet (voice-is-cool)/M-vb2+vox2+cnc-ft_mix.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e0716c2f351e79df054554f17c525b899045d2d05e4c839208b975e87d94e6a
|
| 3 |
+
size 19726074
|
models/ReDimNet (voice-is-cool)/M-vb2-ptn.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42c13ce2bcf1ce466afdbe461c8dbe9471fc23204a1480fb4f306f48152f9af3
|
| 3 |
+
size 19714554
|
models/ReDimNet (voice-is-cool)/README.md
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
models/ReDimNet (voice-is-cool)/S-vb2+vox2+cnc-ft_mix.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76fa264eb8e0e07b143fb16b4eac5aa59ac480d63de4cd9691abf798cbe47fb3
|
| 3 |
+
size 13063610
|
models/ReDimNet (voice-is-cool)/S-vb2-ptn.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75dc73ad9088be38e55ea783820438b218d31e0171c2d50bdd8a950836cab5d1
|
| 3 |
+
size 13052090
|
models/ReDimNet (voice-is-cool)/b0-vox2-ft_lm.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68b8507be1f859d49e4cfd0c2d2bd7aa94e6a288a7df21e65276c9a5d5886cb0
|
| 3 |
+
size 4285894
|
models/ReDimNet (voice-is-cool)/b0-vox2-ptn.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7747c59fb22bc0e91f65a29465325fc26bfe889352d795c8099571d479e31b8e
|
| 3 |
+
size 4284704
|
models/ReDimNet (voice-is-cool)/b1-vox2-ft_lm.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e634bbbeb0f6afd9bbbb0606da834f93e23e4869b3954177a5717acc20ea36c
|
| 3 |
+
size 8730606
|
models/ReDimNet (voice-is-cool)/b1-vox2-ptn.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b20597cc5ee7eecd9ff57afe8c278dda3fc5a6d29e75e7ec780bf9dacc4da798
|
| 3 |
+
size 8729876
|
models/ReDimNet (voice-is-cool)/b2-vox2-ft_lm.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9b6bb2f6747caa28a41eaf2e372d66b0d1563baef186d18f5e99abd5e71e06f
|
| 3 |
+
size 20582650
|
models/ReDimNet (voice-is-cool)/b2-vox2-ptn.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c18a42926878bc8ac079623fbf36f0bc8054cda1199e96fbe1a3f8e131796647
|
| 3 |
+
size 20581530
|
models/ReDimNet (voice-is-cool)/b3-vox2-ft_lm.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4cf657265bb39464301c0f2db51c3f1014dca44959002560a48f8a6a4a3c4ad
|
| 3 |
+
size 13512475
|
models/ReDimNet (voice-is-cool)/b3-vox2-ptn.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3bd5bf57b7568a3e031bd761e2be02004423842768ec3ad3f6b857155c3ed8d
|
| 3 |
+
size 13509705
|
models/ReDimNet (voice-is-cool)/b4-vox2-ft_lm.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94d8c2e9f5234e7ec7cbc7b74dc773d4ba92f12768a4be61df2d571c2b4a9922
|
| 3 |
+
size 26301422
|
models/ReDimNet (voice-is-cool)/b4-vox2-ptn.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fa26daf3276f54509d170498caf119ac460f6268e7ce4a35e25ef1c7cb1c918
|
| 3 |
+
size 26299310
|
models/ReDimNet (voice-is-cool)/b5-vox2-ft_lm.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b0c11bbf5a3a8bb39e5c072c4192d0b694d8c447cf126d4cd3c7346a04b39c8
|
| 3 |
+
size 31174382
|
models/ReDimNet (voice-is-cool)/b5-vox2-ptn.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb8cc848c92c2a01fe225ee29daffbf3487b8183802a949c00986982755457cd
|
| 3 |
+
size 31172270
|
models/ReDimNet (voice-is-cool)/b6-vox2-ft_lm.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0f3034320c9cceaa8ed7c917a36e0affb501a922631d55c1007660eb1bbedea
|
| 3 |
+
size 60663214
|
models/ReDimNet (voice-is-cool)/b6-vox2-ptn.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b306026f7f469327d7a316105ab21d8d6ac3135d7eae1f5dd45c8ad656d251b2
|
| 3 |
+
size 60661102
|
models/ReDimNet (voice-is-cool)/source.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
https://huggingface.co/voice-is-cool/ReDimNet
|
models/redimnet (wd929)/.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/redimnet (wd929)/README.md
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- speaker
|
| 5 |
+
---
|
models/redimnet (wd929)/redimnet_b6_sphereface2/config.yaml
ADDED
|
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
checkpoint: exp_ngc/redimnet_b6_sphereface2/models/model_95.pt
|
| 2 |
+
data_type: shard
|
| 3 |
+
dataloader_args:
|
| 4 |
+
batch_size: 32
|
| 5 |
+
drop_last: true
|
| 6 |
+
num_workers: 4
|
| 7 |
+
pin_memory: false
|
| 8 |
+
prefetch_factor: 4
|
| 9 |
+
dataset_args:
|
| 10 |
+
aug_prob: 0.6
|
| 11 |
+
fbank_args:
|
| 12 |
+
dither: 1.0
|
| 13 |
+
frame_length: 25
|
| 14 |
+
frame_shift: 10
|
| 15 |
+
num_mel_bins: 72
|
| 16 |
+
filter: true
|
| 17 |
+
filter_args:
|
| 18 |
+
max_num_frames: 800
|
| 19 |
+
min_num_frames: 100
|
| 20 |
+
num_frms: 200
|
| 21 |
+
resample_rate: 16000
|
| 22 |
+
sample_num_per_epoch: 0
|
| 23 |
+
shuffle: true
|
| 24 |
+
shuffle_args:
|
| 25 |
+
shuffle_size: 2500
|
| 26 |
+
spec_aug: false
|
| 27 |
+
spec_aug_args:
|
| 28 |
+
max_f: 8
|
| 29 |
+
max_t: 10
|
| 30 |
+
num_f_mask: 1
|
| 31 |
+
num_t_mask: 1
|
| 32 |
+
prob: 0.6
|
| 33 |
+
speed_perturb: true
|
| 34 |
+
enable_amp: false
|
| 35 |
+
exp_dir: exp_ngc/redimnet_b6_sphereface2
|
| 36 |
+
gpus:
|
| 37 |
+
- 0
|
| 38 |
+
- 1
|
| 39 |
+
- 2
|
| 40 |
+
- 3
|
| 41 |
+
- 4
|
| 42 |
+
- 5
|
| 43 |
+
- 6
|
| 44 |
+
- 7
|
| 45 |
+
local_rank: 0
|
| 46 |
+
log_batch_interval: 100
|
| 47 |
+
loss: CrossEntropyLoss
|
| 48 |
+
loss_args: {}
|
| 49 |
+
margin_scheduler: MarginScheduler
|
| 50 |
+
margin_update:
|
| 51 |
+
epoch_iter: 4265
|
| 52 |
+
final_margin: 0.2
|
| 53 |
+
fix_start_epoch: 40
|
| 54 |
+
increase_start_epoch: 20
|
| 55 |
+
increase_type: exp
|
| 56 |
+
initial_margin: 0.0
|
| 57 |
+
update_margin: true
|
| 58 |
+
model: ReDimNetB6
|
| 59 |
+
model_args:
|
| 60 |
+
embed_dim: 192
|
| 61 |
+
feat_dim: 72
|
| 62 |
+
pooling_func: ASTP
|
| 63 |
+
two_emb_layer: false
|
| 64 |
+
model_init: null
|
| 65 |
+
noise_data: data/musan/lmdb
|
| 66 |
+
num_avg: 10
|
| 67 |
+
num_epochs: 120
|
| 68 |
+
optimizer: SGD
|
| 69 |
+
optimizer_args:
|
| 70 |
+
lr: 0.1
|
| 71 |
+
momentum: 0.9
|
| 72 |
+
nesterov: true
|
| 73 |
+
weight_decay: 2.0e-05
|
| 74 |
+
projection_args:
|
| 75 |
+
do_lm: false
|
| 76 |
+
easy_margin: false
|
| 77 |
+
embed_dim: 192
|
| 78 |
+
num_class: 17982
|
| 79 |
+
project_type: sphereface2
|
| 80 |
+
scale: 32.0
|
| 81 |
+
reverb_data: data/rirs/lmdb
|
| 82 |
+
save_epoch_interval: 5
|
| 83 |
+
scheduler: ExponentialDecrease
|
| 84 |
+
scheduler_args:
|
| 85 |
+
epoch_iter: 4265
|
| 86 |
+
final_lr: 5.0e-05
|
| 87 |
+
initial_lr: 0.1
|
| 88 |
+
num_epochs: 120
|
| 89 |
+
scale_ratio: 4.0
|
| 90 |
+
warm_from_zero: true
|
| 91 |
+
warm_up_epoch: 6
|
| 92 |
+
seed: 42
|
| 93 |
+
train_data: data/vox2_dev/shard.list
|
| 94 |
+
train_label: data/vox2_dev/utt2spk
|
models/redimnet (wd929)/redimnet_b6_sphereface2/models/model_115.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1d71fa77006d63eb3e85e8418494bbfec855c55c877f3b42677d3b4c5c5bb98
|
| 3 |
+
size 74370819
|
models/redimnet (wd929)/redimnet_b6_sphereface2/models/model_120.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10ee451d5653d0f45991e31663724387ac073c7d502ca16f4a8dd9cc427e92be
|
| 3 |
+
size 74370819
|