niobures commited on
Commit
a12256d
·
verified ·
1 Parent(s): 3743f14

SSLZip (code, models, paper)

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ SSLZip.[[:space:]]Simple[[:space:]]Autoencoding[[:space:]]for[[:space:]]Enhancing[[:space:]]Self-Supervised[[:space:]]Speech[[:space:]]Representations[[:space:]]in[[:space:]]Speech[[:space:]]Generation.pdf filter=lfs diff=lfs merge=lfs -text
SSLZip. Simple Autoencoding for Enhancing Self-Supervised Speech Representations in Speech Generation.pdf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b68550ee982872dd589d8baf4fcd19cdfcf59c1caed33c01583ecd4a318a7fa9
3
+ size 1529359
code/SSLZip.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb8c22b3557eab6a431818338494f2f801e18a23214e49580b1f09a2e96362e1
3
+ size 31202
models/SSLZip-16/.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/SSLZip-16/LICENSE ADDED
@@ -0,0 +1,325 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Creative Commons Attribution 4.0 International
2
+
3
+ Creative Commons Corporation ("Creative Commons") is not a law firm and
4
+ does not provide legal services or legal advice. Distribution of
5
+ Creative Commons public licenses does not create a lawyer-client or
6
+ other relationship. Creative Commons makes its licenses and related
7
+ information available on an "as-is" basis. Creative Commons gives no
8
+ warranties regarding its licenses, any material licensed under their
9
+ terms and conditions, or any related information. Creative Commons
10
+ disclaims all liability for damages resulting from their use to the
11
+ fullest extent possible.
12
+
13
+ Using Creative Commons Public Licenses
14
+
15
+ Creative Commons public licenses provide a standard set of terms and
16
+ conditions that creators and other rights holders may use to share
17
+ original works of authorship and other material subject to copyright and
18
+ certain other rights specified in the public license below. The
19
+ following considerations are for informational purposes only, are not
20
+ exhaustive, and do not form part of our licenses.
21
+
22
+ Considerations for licensors: Our public licenses are intended for use
23
+ by those authorized to give the public permission to use material in
24
+ ways otherwise restricted by copyright and certain other rights. Our
25
+ licenses are irrevocable. Licensors should read and understand the terms
26
+ and conditions of the license they choose before applying it. Licensors
27
+ should also secure all rights necessary before applying our licenses so
28
+ that the public can reuse the material as expected. Licensors should
29
+ clearly mark any material not subject to the license. This includes
30
+ other CC-licensed material, or material used under an exception or
31
+ limitation to copyright. More considerations for licensors :
32
+ wiki.creativecommons.org/Considerations_for_licensors
33
+
34
+ Considerations for the public: By using one of our public licenses, a
35
+ licensor grants the public permission to use the licensed material under
36
+ specified terms and conditions. If the licensor's permission is not
37
+ necessary for any reason–for example, because of any applicable
38
+ exception or limitation to copyright–then that use is not regulated by
39
+ the license. Our licenses grant only permissions under copyright and
40
+ certain other rights that a licensor has authority to grant. Use of the
41
+ licensed material may still be restricted for other reasons, including
42
+ because others have copyright or other rights in the material. A
43
+ licensor may make special requests, such as asking that all changes be
44
+ marked or described. Although not required by our licenses, you are
45
+ encouraged to respect those requests where reasonable. More
46
+ considerations for the public :
47
+ wiki.creativecommons.org/Considerations_for_licensees
48
+
49
+ Creative Commons Attribution 4.0 International Public License
50
+
51
+ By exercising the Licensed Rights (defined below), You accept and agree
52
+ to be bound by the terms and conditions of this Creative Commons
53
+ Attribution 4.0 International Public License ("Public License"). To the
54
+ extent this Public License may be interpreted as a contract, You are
55
+ granted the Licensed Rights in consideration of Your acceptance of these
56
+ terms and conditions, and the Licensor grants You such rights in
57
+ consideration of benefits the Licensor receives from making the Licensed
58
+ Material available under these terms and conditions.
59
+
60
+ Section 1 – Definitions.
61
+
62
+ - a. Adapted Material means material subject to Copyright and Similar
63
+ Rights that is derived from or based upon the Licensed Material and
64
+ in which the Licensed Material is translated, altered, arranged,
65
+ transformed, or otherwise modified in a manner requiring permission
66
+ under the Copyright and Similar Rights held by the Licensor. For
67
+ purposes of this Public License, where the Licensed Material is a
68
+ musical work, performance, or sound recording, Adapted Material is
69
+ always produced where the Licensed Material is synched in timed
70
+ relation with a moving image.
71
+ - b. Adapter's License means the license You apply to Your Copyright
72
+ and Similar Rights in Your contributions to Adapted Material in
73
+ accordance with the terms and conditions of this Public License.
74
+ - c. Copyright and Similar Rights means copyright and/or similar
75
+ rights closely related to copyright including, without limitation,
76
+ performance, broadcast, sound recording, and Sui Generis Database
77
+ Rights, without regard to how the rights are labeled or categorized.
78
+ For purposes of this Public License, the rights specified in Section
79
+ 2(b)(1)-(2) are not Copyright and Similar Rights.
80
+ - d. Effective Technological Measures means those measures that, in
81
+ the absence of proper authority, may not be circumvented under laws
82
+ fulfilling obligations under Article 11 of the WIPO Copyright Treaty
83
+ adopted on December 20, 1996, and/or similar international
84
+ agreements.
85
+ - e. Exceptions and Limitations means fair use, fair dealing, and/or
86
+ any other exception or limitation to Copyright and Similar Rights
87
+ that applies to Your use of the Licensed Material.
88
+ - f. Licensed Material means the artistic or literary work, database,
89
+ or other material to which the Licensor applied this Public License.
90
+ - g. Licensed Rights means the rights granted to You subject to the
91
+ terms and conditions of this Public License, which are limited to
92
+ all Copyright and Similar Rights that apply to Your use of the
93
+ Licensed Material and that the Licensor has authority to license.
94
+ - h. Licensor means the individual(s) or entity(ies) granting rights
95
+ under this Public License.
96
+ - i. Share means to provide material to the public by any means or
97
+ process that requires permission under the Licensed Rights, such as
98
+ reproduction, public display, public performance, distribution,
99
+ dissemination, communication, or importation, and to make material
100
+ available to the public including in ways that members of the public
101
+ may access the material from a place and at a time individually
102
+ chosen by them.
103
+ - j. Sui Generis Database Rights means rights other than copyright
104
+ resulting from Directive 96/9/EC of the European Parliament and of
105
+ the Council of 11 March 1996 on the legal protection of databases,
106
+ as amended and/or succeeded, as well as other essentially equivalent
107
+ rights anywhere in the world.
108
+ - k. You means the individual or entity exercising the Licensed Rights
109
+ under this Public License. Your has a corresponding meaning.
110
+
111
+ Section 2 – Scope.
112
+
113
+ - a. License grant.
114
+ - 1. Subject to the terms and conditions of this Public License,
115
+ the Licensor hereby grants You a worldwide, royalty-free,
116
+ non-sublicensable, non-exclusive, irrevocable license to
117
+ exercise the Licensed Rights in the Licensed Material to:
118
+ - A. reproduce and Share the Licensed Material, in whole or in
119
+ part; and
120
+ - B. produce, reproduce, and Share Adapted Material.
121
+ - 2. Exceptions and Limitations. For the avoidance of doubt, where
122
+ Exceptions and Limitations apply to Your use, this Public
123
+ License does not apply, and You do not need to comply with its
124
+ terms and conditions.
125
+ - 3. Term. The term of this Public License is specified in Section
126
+ 6(a).
127
+ - 4. Media and formats; technical modifications allowed. The
128
+ Licensor authorizes You to exercise the Licensed Rights in all
129
+ media and formats whether now known or hereafter created, and to
130
+ make technical modifications necessary to do so. The Licensor
131
+ waives and/or agrees not to assert any right or authority to
132
+ forbid You from making technical modifications necessary to
133
+ exercise the Licensed Rights, including technical modifications
134
+ necessary to circumvent Effective Technological Measures. For
135
+ purposes of this Public License, simply making modifications
136
+ authorized by this Section 2(a)(4) never produces Adapted
137
+ Material.
138
+ - 5. Downstream recipients.
139
+ - A. Offer from the Licensor – Licensed Material. Every
140
+ recipient of the Licensed Material automatically receives an
141
+ offer from the Licensor to exercise the Licensed Rights
142
+ under the terms and conditions of this Public License.
143
+ - B. No downstream restrictions. You may not offer or impose
144
+ any additional or different terms or conditions on, or apply
145
+ any Effective Technological Measures to, the Licensed
146
+ Material if doing so restricts exercise of the Licensed
147
+ Rights by any recipient of the Licensed Material.
148
+ - 6. No endorsement. Nothing in this Public License constitutes or
149
+ may be construed as permission to assert or imply that You are,
150
+ or that Your use of the Licensed Material is, connected with, or
151
+ sponsored, endorsed, or granted official status by, the Licensor
152
+ or others designated to receive attribution as provided in
153
+ Section 3(a)(1)(A)(i).
154
+ - b. Other rights.
155
+ - 1. Moral rights, such as the right of integrity, are not
156
+ licensed under this Public License, nor are publicity, privacy,
157
+ and/or other similar personality rights; however, to the extent
158
+ possible, the Licensor waives and/or agrees not to assert any
159
+ such rights held by the Licensor to the limited extent necessary
160
+ to allow You to exercise the Licensed Rights, but not otherwise.
161
+ - 2. Patent and trademark rights are not licensed under this
162
+ Public License.
163
+ - 3. To the extent possible, the Licensor waives any right to
164
+ collect royalties from You for the exercise of the Licensed
165
+ Rights, whether directly or through a collecting society under
166
+ any voluntary or waivable statutory or compulsory licensing
167
+ scheme. In all other cases the Licensor expressly reserves any
168
+ right to collect such royalties.
169
+
170
+ Section 3 – License Conditions.
171
+
172
+ Your exercise of the Licensed Rights is expressly made subject to the
173
+ following conditions.
174
+
175
+ - a. Attribution.
176
+ - 1. If You Share the Licensed Material (including in modified
177
+ form), You must:
178
+ - A. retain the following if it is supplied by the Licensor
179
+ with the Licensed Material:
180
+ - i. identification of the creator(s) of the Licensed
181
+ Material and any others designated to receive
182
+ attribution, in any reasonable manner requested by the
183
+ Licensor (including by pseudonym if designated);
184
+ - ii. a copyright notice;
185
+ - iii. a notice that refers to this Public License;
186
+ - iv. a notice that refers to the disclaimer of
187
+ warranties;
188
+ - v. a URI or hyperlink to the Licensed Material to the
189
+ extent reasonably practicable;
190
+ - B. indicate if You modified the Licensed Material and retain
191
+ an indication of any previous modifications; and
192
+ - C. indicate the Licensed Material is licensed under this
193
+ Public License, and include the text of, or the URI or
194
+ hyperlink to, this Public License.
195
+ - 2. You may satisfy the conditions in Section 3(a)(1) in any
196
+ reasonable manner based on the medium, means, and context in
197
+ which You Share the Licensed Material. For example, it may be
198
+ reasonable to satisfy the conditions by providing a URI or
199
+ hyperlink to a resource that includes the required information.
200
+ - 3. If requested by the Licensor, You must remove any of the
201
+ information required by Section 3(a)(1)(A) to the extent
202
+ reasonably practicable.
203
+ - 4. If You Share Adapted Material You produce, the Adapter's
204
+ License You apply must not prevent recipients of the Adapted
205
+ Material from complying with this Public License.
206
+
207
+ Section 4 – Sui Generis Database Rights.
208
+
209
+ Where the Licensed Rights include Sui Generis Database Rights that apply
210
+ to Your use of the Licensed Material:
211
+
212
+ - a. for the avoidance of doubt, Section 2(a)(1) grants You the right
213
+ to extract, reuse, reproduce, and Share all or a substantial portion
214
+ of the contents of the database;
215
+ - b. if You include all or a substantial portion of the database
216
+ contents in a database in which You have Sui Generis Database
217
+ Rights, then the database in which You have Sui Generis Database
218
+ Rights (but not its individual contents) is Adapted Material; and
219
+ - c. You must comply with the conditions in Section 3(a) if You Share
220
+ all or a substantial portion of the contents of the database.
221
+
222
+ For the avoidance of doubt, this Section 4 supplements and does not
223
+ replace Your obligations under this Public License where the Licensed
224
+ Rights include other Copyright and Similar Rights.
225
+
226
+ Section 5 – Disclaimer of Warranties and Limitation of Liability.
227
+
228
+ - a. Unless otherwise separately undertaken by the Licensor, to the
229
+ extent possible, the Licensor offers the Licensed Material as-is and
230
+ as-available, and makes no representations or warranties of any kind
231
+ concerning the Licensed Material, whether express, implied,
232
+ statutory, or other. This includes, without limitation, warranties
233
+ of title, merchantability, fitness for a particular purpose,
234
+ non-infringement, absence of latent or other defects, accuracy, or
235
+ the presence or absence of errors, whether or not known or
236
+ discoverable. Where disclaimers of warranties are not allowed in
237
+ full or in part, this disclaimer may not apply to You.
238
+ - b. To the extent possible, in no event will the Licensor be liable
239
+ to You on any legal theory (including, without limitation,
240
+ negligence) or otherwise for any direct, special, indirect,
241
+ incidental, consequential, punitive, exemplary, or other losses,
242
+ costs, expenses, or damages arising out of this Public License or
243
+ use of the Licensed Material, even if the Licensor has been advised
244
+ of the possibility of such losses, costs, expenses, or damages.
245
+ Where a limitation of liability is not allowed in full or in part,
246
+ this limitation may not apply to You.
247
+ - c. The disclaimer of warranties and limitation of liability provided
248
+ above shall be interpreted in a manner that, to the extent possible,
249
+ most closely approximates an absolute disclaimer and waiver of all
250
+ liability.
251
+
252
+ Section 6 – Term and Termination.
253
+
254
+ - a. This Public License applies for the term of the Copyright and
255
+ Similar Rights licensed here. However, if You fail to comply with
256
+ this Public License, then Your rights under this Public License
257
+ terminate automatically.
258
+ - b. Where Your right to use the Licensed Material has terminated
259
+ under Section 6(a), it reinstates:
260
+ - 1. automatically as of the date the violation is cured, provided
261
+ it is cured within 30 days of Your discovery of the violation;
262
+ or
263
+ - 2. upon express reinstatement by the Licensor.
264
+ - c. For the avoidance of doubt, this Section 6(b) does not affect any
265
+ right the Licensor may have to seek remedies for Your violations of
266
+ this Public License.
267
+ - d. For the avoidance of doubt, the Licensor may also offer the
268
+ Licensed Material under separate terms or conditions or stop
269
+ distributing the Licensed Material at any time; however, doing so
270
+ will not terminate this Public License.
271
+ - e. Sections 1, 5, 6, 7, and 8 survive termination of this Public
272
+ License.
273
+
274
+ Section 7 – Other Terms and Conditions.
275
+
276
+ - a. The Licensor shall not be bound by any additional or different
277
+ terms or conditions communicated by You unless expressly agreed.
278
+ - b. Any arrangements, understandings, or agreements regarding the
279
+ Licensed Material not stated herein are separate from and
280
+ independent of the terms and conditions of this Public License.
281
+
282
+ Section 8 – Interpretation.
283
+
284
+ - a. For the avoidance of doubt, this Public License does not, and
285
+ shall not be interpreted to, reduce, limit, restrict, or impose
286
+ conditions on any use of the Licensed Material that could lawfully
287
+ be made without permission under this Public License.
288
+ - b. To the extent possible, if any provision of this Public License
289
+ is deemed unenforceable, it shall be automatically reformed to the
290
+ minimum extent necessary to make it enforceable. If the provision
291
+ cannot be reformed, it shall be severed from this Public License
292
+ without affecting the enforceability of the remaining terms and
293
+ conditions.
294
+ - c. No term or condition of this Public License will be waived and no
295
+ failure to comply consented to unless expressly agreed to by the
296
+ Licensor.
297
+ - d. Nothing in this Public License constitutes or may be interpreted
298
+ as a limitation upon, or waiver of, any privileges and immunities
299
+ that apply to the Licensor or You, including from the legal
300
+ processes of any jurisdiction or authority.
301
+
302
+ Creative Commons is not a party to its public licenses. Notwithstanding,
303
+ Creative Commons may elect to apply one of its public licenses to
304
+ material it publishes and in those instances will be considered the
305
+ "Licensor." The text of the Creative Commons public licenses is
306
+ dedicated to the public domain under the CC0 Public Domain Dedication.
307
+ Except for the limited purpose of indicating that material is shared
308
+ under a Creative Commons public license or as otherwise permitted by the
309
+ Creative Commons policies published at creativecommons.org/policies,
310
+ Creative Commons does not authorize the use of the trademark "Creative
311
+ Commons" or any other trademark or logo of Creative Commons without its
312
+ prior written consent including, without limitation, in connection with
313
+ any unauthorized modifications to any of its public licenses or any
314
+ other arrangements, understandings, or agreements concerning use of
315
+ licensed material. For the avoidance of doubt, this paragraph does not
316
+ form part of the public licenses.
317
+
318
+ Creative Commons may be contacted at creativecommons.org.
319
+
320
+ ---
321
+
322
+ Copyright (c) 2025 Nagoya Institute of Technology and Techno-Speech, Inc.
323
+
324
+ This model was trained using the LibriSpeech ASR corpus (c) 2014 by
325
+ Vassil Panayotov, licensed under CC BY 4.0.
models/SSLZip-16/README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-4.0
3
+ datasets:
4
+ - openslr/librispeech_asr
5
+ language:
6
+ - en
7
+ pipeline_tag: audio-to-audio
8
+ ---
9
+
10
+ # SSLZip
11
+
12
+ ## Usage
13
+
14
+ ```py
15
+ import onnxruntime as ort
16
+ from transformers import HubertModel
17
+ import torch
18
+
19
+ # Load the upstream HuBERT model.
20
+ upstream = HubertModel.from_pretrained("facebook/hubert-base-ls960")
21
+ upstream.eval()
22
+
23
+ # Load the autoencoder model.
24
+ postprocessor = ort.InferenceSession("sslzip_16.onnx")
25
+ node_name = postprocessor.get_inputs()[0].name
26
+
27
+ # Prepare an input waveform (assuming 16kHz audio).
28
+ x = torch.randn(1, 16000)
29
+
30
+ # Extract the latent representation for downstream tasks.
31
+ with torch.inference_mode():
32
+ h = upstream(x, output_hidden_states=True).hidden_states[-1]
33
+ z = postprocessor.run(None, {node_name: h.cpu().numpy()})[0]
34
+
35
+ # Use z as you like.
36
+ print(z.shape)
37
+ ```
38
+
39
+ ## License
40
+
41
+ The pretrained model was developed using the LibriSpeech corpus and is distributed under the same license (CC BY 4.0).
42
+ Please include credit to Nagoya Institue of Technology and Techno-Speech, Inc. when using this model.
43
+
44
+ ## Citation
45
+
46
+ ```bibtex
47
+ @InProceedings{yoshimura2025sslzip,
48
+ author = {Takenori Yoshimura and Shinji Takaki and Kazuhiro Nakamura and Keiichiro Oura and Takato Fujimoto and Kei Hashimoto and Yoshihiko Nankaku and Keiichi Tokuda},
49
+ title = {{SSLZip}: Simple autoencoding for enhancing self-supervised speech representations in speech generation},
50
+ booktitle = {13th ISCA Speech Synthesis Workshop (SSW 2025)},
51
+ pages = {xxx--xxx},
52
+ year = {2025},
53
+ }
54
+ ```
models/SSLZip-16/source.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ https://huggingface.co/takenori-y/SSLZip-16
models/SSLZip-16/sslzip_16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9e01fbe9b55a18cebf9881f0c2ae1bb9a51ffe348230cd9d55467f3f6069ee6
3
+ size 110518954
models/SSLZip-256-CLUB/.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/SSLZip-256-CLUB/LICENSE ADDED
@@ -0,0 +1,325 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Creative Commons Attribution 4.0 International
2
+
3
+ Creative Commons Corporation ("Creative Commons") is not a law firm and
4
+ does not provide legal services or legal advice. Distribution of
5
+ Creative Commons public licenses does not create a lawyer-client or
6
+ other relationship. Creative Commons makes its licenses and related
7
+ information available on an "as-is" basis. Creative Commons gives no
8
+ warranties regarding its licenses, any material licensed under their
9
+ terms and conditions, or any related information. Creative Commons
10
+ disclaims all liability for damages resulting from their use to the
11
+ fullest extent possible.
12
+
13
+ Using Creative Commons Public Licenses
14
+
15
+ Creative Commons public licenses provide a standard set of terms and
16
+ conditions that creators and other rights holders may use to share
17
+ original works of authorship and other material subject to copyright and
18
+ certain other rights specified in the public license below. The
19
+ following considerations are for informational purposes only, are not
20
+ exhaustive, and do not form part of our licenses.
21
+
22
+ Considerations for licensors: Our public licenses are intended for use
23
+ by those authorized to give the public permission to use material in
24
+ ways otherwise restricted by copyright and certain other rights. Our
25
+ licenses are irrevocable. Licensors should read and understand the terms
26
+ and conditions of the license they choose before applying it. Licensors
27
+ should also secure all rights necessary before applying our licenses so
28
+ that the public can reuse the material as expected. Licensors should
29
+ clearly mark any material not subject to the license. This includes
30
+ other CC-licensed material, or material used under an exception or
31
+ limitation to copyright. More considerations for licensors :
32
+ wiki.creativecommons.org/Considerations_for_licensors
33
+
34
+ Considerations for the public: By using one of our public licenses, a
35
+ licensor grants the public permission to use the licensed material under
36
+ specified terms and conditions. If the licensor's permission is not
37
+ necessary for any reason–for example, because of any applicable
38
+ exception or limitation to copyright–then that use is not regulated by
39
+ the license. Our licenses grant only permissions under copyright and
40
+ certain other rights that a licensor has authority to grant. Use of the
41
+ licensed material may still be restricted for other reasons, including
42
+ because others have copyright or other rights in the material. A
43
+ licensor may make special requests, such as asking that all changes be
44
+ marked or described. Although not required by our licenses, you are
45
+ encouraged to respect those requests where reasonable. More
46
+ considerations for the public :
47
+ wiki.creativecommons.org/Considerations_for_licensees
48
+
49
+ Creative Commons Attribution 4.0 International Public License
50
+
51
+ By exercising the Licensed Rights (defined below), You accept and agree
52
+ to be bound by the terms and conditions of this Creative Commons
53
+ Attribution 4.0 International Public License ("Public License"). To the
54
+ extent this Public License may be interpreted as a contract, You are
55
+ granted the Licensed Rights in consideration of Your acceptance of these
56
+ terms and conditions, and the Licensor grants You such rights in
57
+ consideration of benefits the Licensor receives from making the Licensed
58
+ Material available under these terms and conditions.
59
+
60
+ Section 1 – Definitions.
61
+
62
+ - a. Adapted Material means material subject to Copyright and Similar
63
+ Rights that is derived from or based upon the Licensed Material and
64
+ in which the Licensed Material is translated, altered, arranged,
65
+ transformed, or otherwise modified in a manner requiring permission
66
+ under the Copyright and Similar Rights held by the Licensor. For
67
+ purposes of this Public License, where the Licensed Material is a
68
+ musical work, performance, or sound recording, Adapted Material is
69
+ always produced where the Licensed Material is synched in timed
70
+ relation with a moving image.
71
+ - b. Adapter's License means the license You apply to Your Copyright
72
+ and Similar Rights in Your contributions to Adapted Material in
73
+ accordance with the terms and conditions of this Public License.
74
+ - c. Copyright and Similar Rights means copyright and/or similar
75
+ rights closely related to copyright including, without limitation,
76
+ performance, broadcast, sound recording, and Sui Generis Database
77
+ Rights, without regard to how the rights are labeled or categorized.
78
+ For purposes of this Public License, the rights specified in Section
79
+ 2(b)(1)-(2) are not Copyright and Similar Rights.
80
+ - d. Effective Technological Measures means those measures that, in
81
+ the absence of proper authority, may not be circumvented under laws
82
+ fulfilling obligations under Article 11 of the WIPO Copyright Treaty
83
+ adopted on December 20, 1996, and/or similar international
84
+ agreements.
85
+ - e. Exceptions and Limitations means fair use, fair dealing, and/or
86
+ any other exception or limitation to Copyright and Similar Rights
87
+ that applies to Your use of the Licensed Material.
88
+ - f. Licensed Material means the artistic or literary work, database,
89
+ or other material to which the Licensor applied this Public License.
90
+ - g. Licensed Rights means the rights granted to You subject to the
91
+ terms and conditions of this Public License, which are limited to
92
+ all Copyright and Similar Rights that apply to Your use of the
93
+ Licensed Material and that the Licensor has authority to license.
94
+ - h. Licensor means the individual(s) or entity(ies) granting rights
95
+ under this Public License.
96
+ - i. Share means to provide material to the public by any means or
97
+ process that requires permission under the Licensed Rights, such as
98
+ reproduction, public display, public performance, distribution,
99
+ dissemination, communication, or importation, and to make material
100
+ available to the public including in ways that members of the public
101
+ may access the material from a place and at a time individually
102
+ chosen by them.
103
+ - j. Sui Generis Database Rights means rights other than copyright
104
+ resulting from Directive 96/9/EC of the European Parliament and of
105
+ the Council of 11 March 1996 on the legal protection of databases,
106
+ as amended and/or succeeded, as well as other essentially equivalent
107
+ rights anywhere in the world.
108
+ - k. You means the individual or entity exercising the Licensed Rights
109
+ under this Public License. Your has a corresponding meaning.
110
+
111
+ Section 2 – Scope.
112
+
113
+ - a. License grant.
114
+ - 1. Subject to the terms and conditions of this Public License,
115
+ the Licensor hereby grants You a worldwide, royalty-free,
116
+ non-sublicensable, non-exclusive, irrevocable license to
117
+ exercise the Licensed Rights in the Licensed Material to:
118
+ - A. reproduce and Share the Licensed Material, in whole or in
119
+ part; and
120
+ - B. produce, reproduce, and Share Adapted Material.
121
+ - 2. Exceptions and Limitations. For the avoidance of doubt, where
122
+ Exceptions and Limitations apply to Your use, this Public
123
+ License does not apply, and You do not need to comply with its
124
+ terms and conditions.
125
+ - 3. Term. The term of this Public License is specified in Section
126
+ 6(a).
127
+ - 4. Media and formats; technical modifications allowed. The
128
+ Licensor authorizes You to exercise the Licensed Rights in all
129
+ media and formats whether now known or hereafter created, and to
130
+ make technical modifications necessary to do so. The Licensor
131
+ waives and/or agrees not to assert any right or authority to
132
+ forbid You from making technical modifications necessary to
133
+ exercise the Licensed Rights, including technical modifications
134
+ necessary to circumvent Effective Technological Measures. For
135
+ purposes of this Public License, simply making modifications
136
+ authorized by this Section 2(a)(4) never produces Adapted
137
+ Material.
138
+ - 5. Downstream recipients.
139
+ - A. Offer from the Licensor – Licensed Material. Every
140
+ recipient of the Licensed Material automatically receives an
141
+ offer from the Licensor to exercise the Licensed Rights
142
+ under the terms and conditions of this Public License.
143
+ - B. No downstream restrictions. You may not offer or impose
144
+ any additional or different terms or conditions on, or apply
145
+ any Effective Technological Measures to, the Licensed
146
+ Material if doing so restricts exercise of the Licensed
147
+ Rights by any recipient of the Licensed Material.
148
+ - 6. No endorsement. Nothing in this Public License constitutes or
149
+ may be construed as permission to assert or imply that You are,
150
+ or that Your use of the Licensed Material is, connected with, or
151
+ sponsored, endorsed, or granted official status by, the Licensor
152
+ or others designated to receive attribution as provided in
153
+ Section 3(a)(1)(A)(i).
154
+ - b. Other rights.
155
+ - 1. Moral rights, such as the right of integrity, are not
156
+ licensed under this Public License, nor are publicity, privacy,
157
+ and/or other similar personality rights; however, to the extent
158
+ possible, the Licensor waives and/or agrees not to assert any
159
+ such rights held by the Licensor to the limited extent necessary
160
+ to allow You to exercise the Licensed Rights, but not otherwise.
161
+ - 2. Patent and trademark rights are not licensed under this
162
+ Public License.
163
+ - 3. To the extent possible, the Licensor waives any right to
164
+ collect royalties from You for the exercise of the Licensed
165
+ Rights, whether directly or through a collecting society under
166
+ any voluntary or waivable statutory or compulsory licensing
167
+ scheme. In all other cases the Licensor expressly reserves any
168
+ right to collect such royalties.
169
+
170
+ Section 3 – License Conditions.
171
+
172
+ Your exercise of the Licensed Rights is expressly made subject to the
173
+ following conditions.
174
+
175
+ - a. Attribution.
176
+ - 1. If You Share the Licensed Material (including in modified
177
+ form), You must:
178
+ - A. retain the following if it is supplied by the Licensor
179
+ with the Licensed Material:
180
+ - i. identification of the creator(s) of the Licensed
181
+ Material and any others designated to receive
182
+ attribution, in any reasonable manner requested by the
183
+ Licensor (including by pseudonym if designated);
184
+ - ii. a copyright notice;
185
+ - iii. a notice that refers to this Public License;
186
+ - iv. a notice that refers to the disclaimer of
187
+ warranties;
188
+ - v. a URI or hyperlink to the Licensed Material to the
189
+ extent reasonably practicable;
190
+ - B. indicate if You modified the Licensed Material and retain
191
+ an indication of any previous modifications; and
192
+ - C. indicate the Licensed Material is licensed under this
193
+ Public License, and include the text of, or the URI or
194
+ hyperlink to, this Public License.
195
+ - 2. You may satisfy the conditions in Section 3(a)(1) in any
196
+ reasonable manner based on the medium, means, and context in
197
+ which You Share the Licensed Material. For example, it may be
198
+ reasonable to satisfy the conditions by providing a URI or
199
+ hyperlink to a resource that includes the required information.
200
+ - 3. If requested by the Licensor, You must remove any of the
201
+ information required by Section 3(a)(1)(A) to the extent
202
+ reasonably practicable.
203
+ - 4. If You Share Adapted Material You produce, the Adapter's
204
+ License You apply must not prevent recipients of the Adapted
205
+ Material from complying with this Public License.
206
+
207
+ Section 4 – Sui Generis Database Rights.
208
+
209
+ Where the Licensed Rights include Sui Generis Database Rights that apply
210
+ to Your use of the Licensed Material:
211
+
212
+ - a. for the avoidance of doubt, Section 2(a)(1) grants You the right
213
+ to extract, reuse, reproduce, and Share all or a substantial portion
214
+ of the contents of the database;
215
+ - b. if You include all or a substantial portion of the database
216
+ contents in a database in which You have Sui Generis Database
217
+ Rights, then the database in which You have Sui Generis Database
218
+ Rights (but not its individual contents) is Adapted Material; and
219
+ - c. You must comply with the conditions in Section 3(a) if You Share
220
+ all or a substantial portion of the contents of the database.
221
+
222
+ For the avoidance of doubt, this Section 4 supplements and does not
223
+ replace Your obligations under this Public License where the Licensed
224
+ Rights include other Copyright and Similar Rights.
225
+
226
+ Section 5 – Disclaimer of Warranties and Limitation of Liability.
227
+
228
+ - a. Unless otherwise separately undertaken by the Licensor, to the
229
+ extent possible, the Licensor offers the Licensed Material as-is and
230
+ as-available, and makes no representations or warranties of any kind
231
+ concerning the Licensed Material, whether express, implied,
232
+ statutory, or other. This includes, without limitation, warranties
233
+ of title, merchantability, fitness for a particular purpose,
234
+ non-infringement, absence of latent or other defects, accuracy, or
235
+ the presence or absence of errors, whether or not known or
236
+ discoverable. Where disclaimers of warranties are not allowed in
237
+ full or in part, this disclaimer may not apply to You.
238
+ - b. To the extent possible, in no event will the Licensor be liable
239
+ to You on any legal theory (including, without limitation,
240
+ negligence) or otherwise for any direct, special, indirect,
241
+ incidental, consequential, punitive, exemplary, or other losses,
242
+ costs, expenses, or damages arising out of this Public License or
243
+ use of the Licensed Material, even if the Licensor has been advised
244
+ of the possibility of such losses, costs, expenses, or damages.
245
+ Where a limitation of liability is not allowed in full or in part,
246
+ this limitation may not apply to You.
247
+ - c. The disclaimer of warranties and limitation of liability provided
248
+ above shall be interpreted in a manner that, to the extent possible,
249
+ most closely approximates an absolute disclaimer and waiver of all
250
+ liability.
251
+
252
+ Section 6 – Term and Termination.
253
+
254
+ - a. This Public License applies for the term of the Copyright and
255
+ Similar Rights licensed here. However, if You fail to comply with
256
+ this Public License, then Your rights under this Public License
257
+ terminate automatically.
258
+ - b. Where Your right to use the Licensed Material has terminated
259
+ under Section 6(a), it reinstates:
260
+ - 1. automatically as of the date the violation is cured, provided
261
+ it is cured within 30 days of Your discovery of the violation;
262
+ or
263
+ - 2. upon express reinstatement by the Licensor.
264
+ - c. For the avoidance of doubt, this Section 6(b) does not affect any
265
+ right the Licensor may have to seek remedies for Your violations of
266
+ this Public License.
267
+ - d. For the avoidance of doubt, the Licensor may also offer the
268
+ Licensed Material under separate terms or conditions or stop
269
+ distributing the Licensed Material at any time; however, doing so
270
+ will not terminate this Public License.
271
+ - e. Sections 1, 5, 6, 7, and 8 survive termination of this Public
272
+ License.
273
+
274
+ Section 7 – Other Terms and Conditions.
275
+
276
+ - a. The Licensor shall not be bound by any additional or different
277
+ terms or conditions communicated by You unless expressly agreed.
278
+ - b. Any arrangements, understandings, or agreements regarding the
279
+ Licensed Material not stated herein are separate from and
280
+ independent of the terms and conditions of this Public License.
281
+
282
+ Section 8 – Interpretation.
283
+
284
+ - a. For the avoidance of doubt, this Public License does not, and
285
+ shall not be interpreted to, reduce, limit, restrict, or impose
286
+ conditions on any use of the Licensed Material that could lawfully
287
+ be made without permission under this Public License.
288
+ - b. To the extent possible, if any provision of this Public License
289
+ is deemed unenforceable, it shall be automatically reformed to the
290
+ minimum extent necessary to make it enforceable. If the provision
291
+ cannot be reformed, it shall be severed from this Public License
292
+ without affecting the enforceability of the remaining terms and
293
+ conditions.
294
+ - c. No term or condition of this Public License will be waived and no
295
+ failure to comply consented to unless expressly agreed to by the
296
+ Licensor.
297
+ - d. Nothing in this Public License constitutes or may be interpreted
298
+ as a limitation upon, or waiver of, any privileges and immunities
299
+ that apply to the Licensor or You, including from the legal
300
+ processes of any jurisdiction or authority.
301
+
302
+ Creative Commons is not a party to its public licenses. Notwithstanding,
303
+ Creative Commons may elect to apply one of its public licenses to
304
+ material it publishes and in those instances will be considered the
305
+ "Licensor." The text of the Creative Commons public licenses is
306
+ dedicated to the public domain under the CC0 Public Domain Dedication.
307
+ Except for the limited purpose of indicating that material is shared
308
+ under a Creative Commons public license or as otherwise permitted by the
309
+ Creative Commons policies published at creativecommons.org/policies,
310
+ Creative Commons does not authorize the use of the trademark "Creative
311
+ Commons" or any other trademark or logo of Creative Commons without its
312
+ prior written consent including, without limitation, in connection with
313
+ any unauthorized modifications to any of its public licenses or any
314
+ other arrangements, understandings, or agreements concerning use of
315
+ licensed material. For the avoidance of doubt, this paragraph does not
316
+ form part of the public licenses.
317
+
318
+ Creative Commons may be contacted at creativecommons.org.
319
+
320
+ ---
321
+
322
+ Copyright (c) 2025 Nagoya Institute of Technology and Techno-Speech, Inc.
323
+
324
+ This model was trained using the LibriSpeech ASR corpus (c) 2014 by
325
+ Vassil Panayotov, licensed under CC BY 4.0.
models/SSLZip-256-CLUB/README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-4.0
3
+ datasets:
4
+ - openslr/librispeech_asr
5
+ language:
6
+ - en
7
+ pipeline_tag: audio-to-audio
8
+ ---
9
+
10
+ # SSLZip
11
+
12
+ ## Usage
13
+
14
+ ```py
15
+ import onnxruntime as ort
16
+ from transformers import HubertModel
17
+ import torch
18
+
19
+ # Load the upstream HuBERT model.
20
+ upstream = HubertModel.from_pretrained("facebook/hubert-base-ls960")
21
+ upstream.eval()
22
+
23
+ # Load the autoencoder model.
24
+ postprocessor = ort.InferenceSession("sslzip_256_club.onnx")
25
+ node_name = postprocessor.get_inputs()[0].name
26
+
27
+ # Prepare an input waveform (assuming 16kHz audio).
28
+ x = torch.randn(1, 16000)
29
+
30
+ # Extract the latent representation for downstream tasks.
31
+ with torch.inference_mode():
32
+ h = upstream(x, output_hidden_states=True).hidden_states[-1]
33
+ z = postprocessor.run(None, {node_name: h.cpu().numpy()})[0]
34
+
35
+ # Use z as you like.
36
+ print(z.shape)
37
+ ```
38
+
39
+ ## License
40
+
41
+ The pretrained model was developed using the LibriSpeech corpus and is distributed under the same license (CC BY 4.0).
42
+ Please include credit to Nagoya Institue of Technology and Techno-Speech, Inc. when using this model.
43
+
44
+ ## Citation
45
+
46
+ ```bibtex
47
+ @InProceedings{yoshimura2025sslzip,
48
+ author = {Takenori Yoshimura and Shinji Takaki and Kazuhiro Nakamura and Keiichiro Oura and Takato Fujimoto and Kei Hashimoto and Yoshihiko Nankaku and Keiichi Tokuda},
49
+ title = {{SSLZip}: Simple autoencoding for enhancing self-supervised speech representations in speech generation},
50
+ booktitle = {13th ISCA Speech Synthesis Workshop (SSW 2025)},
51
+ pages = {xxx--xxx},
52
+ year = {2025},
53
+ }
54
+ ```
models/SSLZip-256-CLUB/source.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ https://huggingface.co/takenori-y/SSLZip-256-CLUB
models/SSLZip-256-CLUB/sslzip_256_club.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:049ca56bfbb9b3d1e15b237f96077c32ca44a2aa54bf2cd56d2a45270e98e7cb
3
+ size 111257199
models/SSLZip-256/.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/SSLZip-256/LICENSE ADDED
@@ -0,0 +1,325 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Creative Commons Attribution 4.0 International
2
+
3
+ Creative Commons Corporation ("Creative Commons") is not a law firm and
4
+ does not provide legal services or legal advice. Distribution of
5
+ Creative Commons public licenses does not create a lawyer-client or
6
+ other relationship. Creative Commons makes its licenses and related
7
+ information available on an "as-is" basis. Creative Commons gives no
8
+ warranties regarding its licenses, any material licensed under their
9
+ terms and conditions, or any related information. Creative Commons
10
+ disclaims all liability for damages resulting from their use to the
11
+ fullest extent possible.
12
+
13
+ Using Creative Commons Public Licenses
14
+
15
+ Creative Commons public licenses provide a standard set of terms and
16
+ conditions that creators and other rights holders may use to share
17
+ original works of authorship and other material subject to copyright and
18
+ certain other rights specified in the public license below. The
19
+ following considerations are for informational purposes only, are not
20
+ exhaustive, and do not form part of our licenses.
21
+
22
+ Considerations for licensors: Our public licenses are intended for use
23
+ by those authorized to give the public permission to use material in
24
+ ways otherwise restricted by copyright and certain other rights. Our
25
+ licenses are irrevocable. Licensors should read and understand the terms
26
+ and conditions of the license they choose before applying it. Licensors
27
+ should also secure all rights necessary before applying our licenses so
28
+ that the public can reuse the material as expected. Licensors should
29
+ clearly mark any material not subject to the license. This includes
30
+ other CC-licensed material, or material used under an exception or
31
+ limitation to copyright. More considerations for licensors :
32
+ wiki.creativecommons.org/Considerations_for_licensors
33
+
34
+ Considerations for the public: By using one of our public licenses, a
35
+ licensor grants the public permission to use the licensed material under
36
+ specified terms and conditions. If the licensor's permission is not
37
+ necessary for any reason–for example, because of any applicable
38
+ exception or limitation to copyright–then that use is not regulated by
39
+ the license. Our licenses grant only permissions under copyright and
40
+ certain other rights that a licensor has authority to grant. Use of the
41
+ licensed material may still be restricted for other reasons, including
42
+ because others have copyright or other rights in the material. A
43
+ licensor may make special requests, such as asking that all changes be
44
+ marked or described. Although not required by our licenses, you are
45
+ encouraged to respect those requests where reasonable. More
46
+ considerations for the public :
47
+ wiki.creativecommons.org/Considerations_for_licensees
48
+
49
+ Creative Commons Attribution 4.0 International Public License
50
+
51
+ By exercising the Licensed Rights (defined below), You accept and agree
52
+ to be bound by the terms and conditions of this Creative Commons
53
+ Attribution 4.0 International Public License ("Public License"). To the
54
+ extent this Public License may be interpreted as a contract, You are
55
+ granted the Licensed Rights in consideration of Your acceptance of these
56
+ terms and conditions, and the Licensor grants You such rights in
57
+ consideration of benefits the Licensor receives from making the Licensed
58
+ Material available under these terms and conditions.
59
+
60
+ Section 1 – Definitions.
61
+
62
+ - a. Adapted Material means material subject to Copyright and Similar
63
+ Rights that is derived from or based upon the Licensed Material and
64
+ in which the Licensed Material is translated, altered, arranged,
65
+ transformed, or otherwise modified in a manner requiring permission
66
+ under the Copyright and Similar Rights held by the Licensor. For
67
+ purposes of this Public License, where the Licensed Material is a
68
+ musical work, performance, or sound recording, Adapted Material is
69
+ always produced where the Licensed Material is synched in timed
70
+ relation with a moving image.
71
+ - b. Adapter's License means the license You apply to Your Copyright
72
+ and Similar Rights in Your contributions to Adapted Material in
73
+ accordance with the terms and conditions of this Public License.
74
+ - c. Copyright and Similar Rights means copyright and/or similar
75
+ rights closely related to copyright including, without limitation,
76
+ performance, broadcast, sound recording, and Sui Generis Database
77
+ Rights, without regard to how the rights are labeled or categorized.
78
+ For purposes of this Public License, the rights specified in Section
79
+ 2(b)(1)-(2) are not Copyright and Similar Rights.
80
+ - d. Effective Technological Measures means those measures that, in
81
+ the absence of proper authority, may not be circumvented under laws
82
+ fulfilling obligations under Article 11 of the WIPO Copyright Treaty
83
+ adopted on December 20, 1996, and/or similar international
84
+ agreements.
85
+ - e. Exceptions and Limitations means fair use, fair dealing, and/or
86
+ any other exception or limitation to Copyright and Similar Rights
87
+ that applies to Your use of the Licensed Material.
88
+ - f. Licensed Material means the artistic or literary work, database,
89
+ or other material to which the Licensor applied this Public License.
90
+ - g. Licensed Rights means the rights granted to You subject to the
91
+ terms and conditions of this Public License, which are limited to
92
+ all Copyright and Similar Rights that apply to Your use of the
93
+ Licensed Material and that the Licensor has authority to license.
94
+ - h. Licensor means the individual(s) or entity(ies) granting rights
95
+ under this Public License.
96
+ - i. Share means to provide material to the public by any means or
97
+ process that requires permission under the Licensed Rights, such as
98
+ reproduction, public display, public performance, distribution,
99
+ dissemination, communication, or importation, and to make material
100
+ available to the public including in ways that members of the public
101
+ may access the material from a place and at a time individually
102
+ chosen by them.
103
+ - j. Sui Generis Database Rights means rights other than copyright
104
+ resulting from Directive 96/9/EC of the European Parliament and of
105
+ the Council of 11 March 1996 on the legal protection of databases,
106
+ as amended and/or succeeded, as well as other essentially equivalent
107
+ rights anywhere in the world.
108
+ - k. You means the individual or entity exercising the Licensed Rights
109
+ under this Public License. Your has a corresponding meaning.
110
+
111
+ Section 2 – Scope.
112
+
113
+ - a. License grant.
114
+ - 1. Subject to the terms and conditions of this Public License,
115
+ the Licensor hereby grants You a worldwide, royalty-free,
116
+ non-sublicensable, non-exclusive, irrevocable license to
117
+ exercise the Licensed Rights in the Licensed Material to:
118
+ - A. reproduce and Share the Licensed Material, in whole or in
119
+ part; and
120
+ - B. produce, reproduce, and Share Adapted Material.
121
+ - 2. Exceptions and Limitations. For the avoidance of doubt, where
122
+ Exceptions and Limitations apply to Your use, this Public
123
+ License does not apply, and You do not need to comply with its
124
+ terms and conditions.
125
+ - 3. Term. The term of this Public License is specified in Section
126
+ 6(a).
127
+ - 4. Media and formats; technical modifications allowed. The
128
+ Licensor authorizes You to exercise the Licensed Rights in all
129
+ media and formats whether now known or hereafter created, and to
130
+ make technical modifications necessary to do so. The Licensor
131
+ waives and/or agrees not to assert any right or authority to
132
+ forbid You from making technical modifications necessary to
133
+ exercise the Licensed Rights, including technical modifications
134
+ necessary to circumvent Effective Technological Measures. For
135
+ purposes of this Public License, simply making modifications
136
+ authorized by this Section 2(a)(4) never produces Adapted
137
+ Material.
138
+ - 5. Downstream recipients.
139
+ - A. Offer from the Licensor – Licensed Material. Every
140
+ recipient of the Licensed Material automatically receives an
141
+ offer from the Licensor to exercise the Licensed Rights
142
+ under the terms and conditions of this Public License.
143
+ - B. No downstream restrictions. You may not offer or impose
144
+ any additional or different terms or conditions on, or apply
145
+ any Effective Technological Measures to, the Licensed
146
+ Material if doing so restricts exercise of the Licensed
147
+ Rights by any recipient of the Licensed Material.
148
+ - 6. No endorsement. Nothing in this Public License constitutes or
149
+ may be construed as permission to assert or imply that You are,
150
+ or that Your use of the Licensed Material is, connected with, or
151
+ sponsored, endorsed, or granted official status by, the Licensor
152
+ or others designated to receive attribution as provided in
153
+ Section 3(a)(1)(A)(i).
154
+ - b. Other rights.
155
+ - 1. Moral rights, such as the right of integrity, are not
156
+ licensed under this Public License, nor are publicity, privacy,
157
+ and/or other similar personality rights; however, to the extent
158
+ possible, the Licensor waives and/or agrees not to assert any
159
+ such rights held by the Licensor to the limited extent necessary
160
+ to allow You to exercise the Licensed Rights, but not otherwise.
161
+ - 2. Patent and trademark rights are not licensed under this
162
+ Public License.
163
+ - 3. To the extent possible, the Licensor waives any right to
164
+ collect royalties from You for the exercise of the Licensed
165
+ Rights, whether directly or through a collecting society under
166
+ any voluntary or waivable statutory or compulsory licensing
167
+ scheme. In all other cases the Licensor expressly reserves any
168
+ right to collect such royalties.
169
+
170
+ Section 3 – License Conditions.
171
+
172
+ Your exercise of the Licensed Rights is expressly made subject to the
173
+ following conditions.
174
+
175
+ - a. Attribution.
176
+ - 1. If You Share the Licensed Material (including in modified
177
+ form), You must:
178
+ - A. retain the following if it is supplied by the Licensor
179
+ with the Licensed Material:
180
+ - i. identification of the creator(s) of the Licensed
181
+ Material and any others designated to receive
182
+ attribution, in any reasonable manner requested by the
183
+ Licensor (including by pseudonym if designated);
184
+ - ii. a copyright notice;
185
+ - iii. a notice that refers to this Public License;
186
+ - iv. a notice that refers to the disclaimer of
187
+ warranties;
188
+ - v. a URI or hyperlink to the Licensed Material to the
189
+ extent reasonably practicable;
190
+ - B. indicate if You modified the Licensed Material and retain
191
+ an indication of any previous modifications; and
192
+ - C. indicate the Licensed Material is licensed under this
193
+ Public License, and include the text of, or the URI or
194
+ hyperlink to, this Public License.
195
+ - 2. You may satisfy the conditions in Section 3(a)(1) in any
196
+ reasonable manner based on the medium, means, and context in
197
+ which You Share the Licensed Material. For example, it may be
198
+ reasonable to satisfy the conditions by providing a URI or
199
+ hyperlink to a resource that includes the required information.
200
+ - 3. If requested by the Licensor, You must remove any of the
201
+ information required by Section 3(a)(1)(A) to the extent
202
+ reasonably practicable.
203
+ - 4. If You Share Adapted Material You produce, the Adapter's
204
+ License You apply must not prevent recipients of the Adapted
205
+ Material from complying with this Public License.
206
+
207
+ Section 4 – Sui Generis Database Rights.
208
+
209
+ Where the Licensed Rights include Sui Generis Database Rights that apply
210
+ to Your use of the Licensed Material:
211
+
212
+ - a. for the avoidance of doubt, Section 2(a)(1) grants You the right
213
+ to extract, reuse, reproduce, and Share all or a substantial portion
214
+ of the contents of the database;
215
+ - b. if You include all or a substantial portion of the database
216
+ contents in a database in which You have Sui Generis Database
217
+ Rights, then the database in which You have Sui Generis Database
218
+ Rights (but not its individual contents) is Adapted Material; and
219
+ - c. You must comply with the conditions in Section 3(a) if You Share
220
+ all or a substantial portion of the contents of the database.
221
+
222
+ For the avoidance of doubt, this Section 4 supplements and does not
223
+ replace Your obligations under this Public License where the Licensed
224
+ Rights include other Copyright and Similar Rights.
225
+
226
+ Section 5 – Disclaimer of Warranties and Limitation of Liability.
227
+
228
+ - a. Unless otherwise separately undertaken by the Licensor, to the
229
+ extent possible, the Licensor offers the Licensed Material as-is and
230
+ as-available, and makes no representations or warranties of any kind
231
+ concerning the Licensed Material, whether express, implied,
232
+ statutory, or other. This includes, without limitation, warranties
233
+ of title, merchantability, fitness for a particular purpose,
234
+ non-infringement, absence of latent or other defects, accuracy, or
235
+ the presence or absence of errors, whether or not known or
236
+ discoverable. Where disclaimers of warranties are not allowed in
237
+ full or in part, this disclaimer may not apply to You.
238
+ - b. To the extent possible, in no event will the Licensor be liable
239
+ to You on any legal theory (including, without limitation,
240
+ negligence) or otherwise for any direct, special, indirect,
241
+ incidental, consequential, punitive, exemplary, or other losses,
242
+ costs, expenses, or damages arising out of this Public License or
243
+ use of the Licensed Material, even if the Licensor has been advised
244
+ of the possibility of such losses, costs, expenses, or damages.
245
+ Where a limitation of liability is not allowed in full or in part,
246
+ this limitation may not apply to You.
247
+ - c. The disclaimer of warranties and limitation of liability provided
248
+ above shall be interpreted in a manner that, to the extent possible,
249
+ most closely approximates an absolute disclaimer and waiver of all
250
+ liability.
251
+
252
+ Section 6 – Term and Termination.
253
+
254
+ - a. This Public License applies for the term of the Copyright and
255
+ Similar Rights licensed here. However, if You fail to comply with
256
+ this Public License, then Your rights under this Public License
257
+ terminate automatically.
258
+ - b. Where Your right to use the Licensed Material has terminated
259
+ under Section 6(a), it reinstates:
260
+ - 1. automatically as of the date the violation is cured, provided
261
+ it is cured within 30 days of Your discovery of the violation;
262
+ or
263
+ - 2. upon express reinstatement by the Licensor.
264
+ - c. For the avoidance of doubt, this Section 6(b) does not affect any
265
+ right the Licensor may have to seek remedies for Your violations of
266
+ this Public License.
267
+ - d. For the avoidance of doubt, the Licensor may also offer the
268
+ Licensed Material under separate terms or conditions or stop
269
+ distributing the Licensed Material at any time; however, doing so
270
+ will not terminate this Public License.
271
+ - e. Sections 1, 5, 6, 7, and 8 survive termination of this Public
272
+ License.
273
+
274
+ Section 7 – Other Terms and Conditions.
275
+
276
+ - a. The Licensor shall not be bound by any additional or different
277
+ terms or conditions communicated by You unless expressly agreed.
278
+ - b. Any arrangements, understandings, or agreements regarding the
279
+ Licensed Material not stated herein are separate from and
280
+ independent of the terms and conditions of this Public License.
281
+
282
+ Section 8 – Interpretation.
283
+
284
+ - a. For the avoidance of doubt, this Public License does not, and
285
+ shall not be interpreted to, reduce, limit, restrict, or impose
286
+ conditions on any use of the Licensed Material that could lawfully
287
+ be made without permission under this Public License.
288
+ - b. To the extent possible, if any provision of this Public License
289
+ is deemed unenforceable, it shall be automatically reformed to the
290
+ minimum extent necessary to make it enforceable. If the provision
291
+ cannot be reformed, it shall be severed from this Public License
292
+ without affecting the enforceability of the remaining terms and
293
+ conditions.
294
+ - c. No term or condition of this Public License will be waived and no
295
+ failure to comply consented to unless expressly agreed to by the
296
+ Licensor.
297
+ - d. Nothing in this Public License constitutes or may be interpreted
298
+ as a limitation upon, or waiver of, any privileges and immunities
299
+ that apply to the Licensor or You, including from the legal
300
+ processes of any jurisdiction or authority.
301
+
302
+ Creative Commons is not a party to its public licenses. Notwithstanding,
303
+ Creative Commons may elect to apply one of its public licenses to
304
+ material it publishes and in those instances will be considered the
305
+ "Licensor." The text of the Creative Commons public licenses is
306
+ dedicated to the public domain under the CC0 Public Domain Dedication.
307
+ Except for the limited purpose of indicating that material is shared
308
+ under a Creative Commons public license or as otherwise permitted by the
309
+ Creative Commons policies published at creativecommons.org/policies,
310
+ Creative Commons does not authorize the use of the trademark "Creative
311
+ Commons" or any other trademark or logo of Creative Commons without its
312
+ prior written consent including, without limitation, in connection with
313
+ any unauthorized modifications to any of its public licenses or any
314
+ other arrangements, understandings, or agreements concerning use of
315
+ licensed material. For the avoidance of doubt, this paragraph does not
316
+ form part of the public licenses.
317
+
318
+ Creative Commons may be contacted at creativecommons.org.
319
+
320
+ ---
321
+
322
+ Copyright (c) 2025 Nagoya Institute of Technology and Techno-Speech, Inc.
323
+
324
+ This model was trained using the LibriSpeech ASR corpus (c) 2014 by
325
+ Vassil Panayotov, licensed under CC BY 4.0.
models/SSLZip-256/README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-4.0
3
+ datasets:
4
+ - openslr/librispeech_asr
5
+ language:
6
+ - en
7
+ pipeline_tag: audio-to-audio
8
+ ---
9
+
10
+ # SSLZip
11
+
12
+ ## Usage
13
+
14
+ ```py
15
+ import onnxruntime as ort
16
+ from transformers import HubertModel
17
+ import torch
18
+
19
+ # Load the upstream HuBERT model.
20
+ upstream = HubertModel.from_pretrained("facebook/hubert-base-ls960")
21
+ upstream.eval()
22
+
23
+ # Load the autoencoder model.
24
+ postprocessor = ort.InferenceSession("sslzip_256.onnx")
25
+ node_name = postprocessor.get_inputs()[0].name
26
+
27
+ # Prepare an input waveform (assuming 16kHz audio).
28
+ x = torch.randn(1, 16000)
29
+
30
+ # Extract the latent representation for downstream tasks.
31
+ with torch.inference_mode():
32
+ h = upstream(x, output_hidden_states=True).hidden_states[-1]
33
+ z = postprocessor.run(None, {node_name: h.cpu().numpy()})[0]
34
+
35
+ # Use z as you like.
36
+ print(z.shape)
37
+ ```
38
+
39
+ ## License
40
+
41
+ The pretrained model was developed using the LibriSpeech corpus and is distributed under the same license (CC BY 4.0).
42
+ Please include credit to Nagoya Institue of Technology and Techno-Speech, Inc. when using this model.
43
+
44
+ ## Citation
45
+
46
+ ```bibtex
47
+ @InProceedings{yoshimura2025sslzip,
48
+ author = {Takenori Yoshimura and Shinji Takaki and Kazuhiro Nakamura and Keiichiro Oura and Takato Fujimoto and Kei Hashimoto and Yoshihiko Nankaku and Keiichi Tokuda},
49
+ title = {{SSLZip}: Simple autoencoding for enhancing self-supervised speech representations in speech generation},
50
+ booktitle = {13th ISCA Speech Synthesis Workshop (SSW 2025)},
51
+ pages = {xxx--xxx},
52
+ year = {2025},
53
+ }
54
+ ```
models/SSLZip-256/source.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ https://huggingface.co/takenori-y/SSLZip-256
models/SSLZip-256/sslzip_256.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9521cf207a2026095d15a9103eb8558de04a55c42086dfd7aff8a4c112685a7
3
+ size 111257199