mrfakename ipoletaev commited on
Commit
8e3bc8a
·
0 Parent(s):

Duplicate from inworld/voice-isolator

Browse files

Co-authored-by: Igor Poletaev <ipoletaev@users.noreply.huggingface.co>

.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
LICENSE ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ Apache License
3
+ Version 2.0, January 2004
4
+ http://www.apache.org/licenses/
5
+
6
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7
+
8
+ 1. Definitions.
9
+
10
+ "License" shall mean the terms and conditions for use, reproduction,
11
+ and distribution as defined by Sections 1 through 9 of this document.
12
+
13
+ "Licensor" shall mean the copyright owner or entity authorized by
14
+ the copyright owner that is granting the License.
15
+
16
+ "Legal Entity" shall mean the union of the acting entity and all
17
+ other entities that control, are controlled by, or are under common
18
+ control with that entity. For the purposes of this definition,
19
+ "control" means (i) the power, direct or indirect, to cause the
20
+ direction or management of such entity, whether by contract or
21
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
22
+ outstanding shares, or (iii) beneficial ownership of such entity.
23
+
24
+ "You" (or "Your") shall mean an individual or Legal Entity
25
+ exercising permissions granted by this License.
26
+
27
+ "Source" form shall mean the preferred form for making modifications,
28
+ including but not limited to software source code, documentation
29
+ source, and configuration files.
30
+
31
+ "Object" form shall mean any form resulting from mechanical
32
+ transformation or translation of a Source form, including but
33
+ not limited to compiled object code, generated documentation,
34
+ and conversions to other media types.
35
+
36
+ "Work" shall mean the work of authorship, whether in Source or
37
+ Object form, made available under the License, as indicated by a
38
+ copyright notice that is included in or attached to the work
39
+ (an example is provided in the Appendix below).
40
+
41
+ "Derivative Works" shall mean any work, whether in Source or Object
42
+ form, that is based on (or derived from) the Work and for which the
43
+ editorial revisions, annotations, elaborations, or other modifications
44
+ represent, as a whole, an original work of authorship. For the purposes
45
+ of this License, Derivative Works shall not include works that remain
46
+ separable from, or merely link (or bind by name) to the interfaces of,
47
+ the Work and Derivative Works thereof.
48
+
49
+ "Contribution" shall mean any work of authorship, including
50
+ the original version of the Work and any modifications or additions
51
+ to that Work or Derivative Works thereof, that is intentionally
52
+ submitted to Licensor for inclusion in the Work by the copyright owner
53
+ or by an individual or Legal Entity authorized to submit on behalf of
54
+ the copyright owner. For the purposes of this definition, "submitted"
55
+ means any form of electronic, verbal, or written communication sent
56
+ to the Licensor or its representatives, including but not limited to
57
+ communication on electronic mailing lists, source code control systems,
58
+ and issue tracking systems that are managed by, or on behalf of, the
59
+ Licensor for the purpose of discussing and improving the Work, but
60
+ excluding communication that is conspicuously marked or otherwise
61
+ designated in writing by the copyright owner as "Not a Contribution."
62
+
63
+ "Contributor" shall mean Licensor and any individual or Legal Entity
64
+ on behalf of whom a Contribution has been received by Licensor and
65
+ subsequently incorporated within the Work.
66
+
67
+ 2. Grant of Copyright License. Subject to the terms and conditions of
68
+ this License, each Contributor hereby grants to You a perpetual,
69
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70
+ copyright license to reproduce, prepare Derivative Works of,
71
+ publicly display, publicly perform, sublicense, and distribute the
72
+ Work and such Derivative Works in Source or Object form.
73
+
74
+ 3. Grant of Patent License. Subject to the terms and conditions of
75
+ this License, each Contributor hereby grants to You a perpetual,
76
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77
+ (except as stated in this section) patent license to make, have made,
78
+ use, offer to sell, sell, import, and otherwise transfer the Work,
79
+ where such license applies only to those patent claims licensable
80
+ by such Contributor that are necessarily infringed by their
81
+ Contribution(s) alone or by combination of their Contribution(s)
82
+ with the Work to which such Contribution(s) was submitted. If You
83
+ institute patent litigation against any entity (including a
84
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
85
+ or a Contribution incorporated within the Work constitutes direct
86
+ or contributory patent infringement, then any patent licenses
87
+ granted to You under this License for that Work shall terminate
88
+ as of the date such litigation is filed.
89
+
90
+ 4. Redistribution. You may reproduce and distribute copies of the
91
+ Work or Derivative Works thereof in any medium, with or without
92
+ modifications, and in Source or Object form, provided that You
93
+ meet the following conditions:
94
+
95
+ (a) You must give any other recipients of the Work or
96
+ Derivative Works a copy of this License; and
97
+
98
+ (b) You must cause any modified files to carry prominent notices
99
+ stating that You changed the files; and
100
+
101
+ (c) You must retain, in the Source form of any Derivative Works
102
+ that You distribute, all copyright, patent, trademark, and
103
+ attribution notices from the Source form of the Work,
104
+ excluding those notices that do not pertain to any part of
105
+ the Derivative Works; and
106
+
107
+ (d) If the Work includes a "NOTICE" text file as part of its
108
+ distribution, then any Derivative Works that You distribute must
109
+ include a readable copy of the attribution notices contained
110
+ within such NOTICE file, excluding those notices that do not
111
+ pertain to any part of the Derivative Works, in at least one
112
+ of the following places: within a NOTICE text file distributed
113
+ as part of the Derivative Works; within the Source form or
114
+ documentation, if provided along with the Derivative Works; or,
115
+ within a display generated by the Derivative Works, if and
116
+ wherever such third-party notices normally appear. The contents
117
+ of the NOTICE file are for informational purposes only and
118
+ do not modify the License. You may add Your own attribution
119
+ notices within Derivative Works that You distribute, alongside
120
+ or as an addendum to the NOTICE text from the Work, provided
121
+ that such additional attribution notices cannot be construed
122
+ as modifying the License.
123
+
124
+ You may add Your own copyright statement to Your modifications and
125
+ may provide additional or different license terms and conditions
126
+ for use, reproduction, or distribution of Your modifications, or
127
+ for any such Derivative Works as a whole, provided Your use,
128
+ reproduction, and distribution of the Work otherwise complies with
129
+ the conditions stated in this License.
130
+
131
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
132
+ any Contribution intentionally submitted for inclusion in the Work
133
+ by You to the Licensor shall be under the terms and conditions of
134
+ this License, without any additional terms or conditions.
135
+ Notwithstanding the above, nothing herein shall supersede or modify
136
+ the terms of any separate license agreement you may have executed
137
+ with Licensor regarding such Contributions.
138
+
139
+ 6. Trademarks. This License does not grant permission to use the trade
140
+ names, trademarks, service marks, or product names of the Licensor,
141
+ except as required for reasonable and customary use in describing the
142
+ origin of the Work and reproducing the content of the NOTICE file.
143
+
144
+ 7. Disclaimer of Warranty. Unless required by applicable law or
145
+ agreed to in writing, Licensor provides the Work (and each
146
+ Contributor provides its Contributions) on an "AS IS" BASIS,
147
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148
+ implied, including, without limitation, any warranties or conditions
149
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150
+ PARTICULAR PURPOSE. You are solely responsible for determining the
151
+ appropriateness of using or redistributing the Work and assume any
152
+ risks associated with Your exercise of permissions under this License.
153
+
154
+ 8. Limitation of Liability. In no event and under no legal theory,
155
+ whether in tort (including negligence), contract, or otherwise,
156
+ unless required by applicable law (such as deliberate and grossly
157
+ negligent acts) or agreed to in writing, shall any Contributor be
158
+ liable to You for damages, including any direct, indirect, special,
159
+ incidental, or consequential damages of any character arising as a
160
+ result of this License or out of the use or inability to use the
161
+ Work (including but not limited to damages for loss of goodwill,
162
+ work stoppage, computer failure or malfunction, or any and all
163
+ other commercial damages or losses), even if such Contributor
164
+ has been advised of the possibility of such damages.
165
+
166
+ 9. Accepting Warranty or Additional Liability. While redistributing
167
+ the Work or Derivative Works thereof, You may choose to offer,
168
+ and charge a fee for, acceptance of support, warranty, indemnity,
169
+ or other liability obligations and/or rights consistent with this
170
+ License. However, in accepting such obligations, You may act only
171
+ on Your own behalf and on Your sole responsibility, not on behalf
172
+ of any other Contributor, and only if You agree to indemnify,
173
+ defend, and hold each Contributor harmless for any liability
174
+ incurred by, or claims asserted against, such Contributor by reason
175
+ of your accepting any such warranty or additional liability.
176
+
177
+ END OF TERMS AND CONDITIONS
178
+
179
+ APPENDIX: How to apply the Apache License to your work.
180
+
181
+ To apply the Apache License to your work, attach the following
182
+ boilerplate notice, with the fields enclosed by brackets "[]"
183
+ replaced with your own identifying information. (Don't include
184
+ the brackets!) The text should be enclosed in the appropriate
185
+ comment syntax for the file format. We also recommend that a
186
+ file or class name and description of purpose be included on the
187
+ same "printed page" as the copyright notice for easier
188
+ identification within third-party archives.
189
+
190
+ Copyright [yyyy] [name of copyright owner]
191
+
192
+ Licensed under the Apache License, Version 2.0 (the "License");
193
+ you may not use this file except in compliance with the License.
194
+ You may obtain a copy of the License at
195
+
196
+ http://www.apache.org/licenses/LICENSE-2.0
197
+
198
+ Unless required by applicable law or agreed to in writing, software
199
+ distributed under the License is distributed on an "AS IS" BASIS,
200
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201
+ See the License for the specific language governing permissions and
202
+ limitations under the License.
NOTICE ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Inworld Voice Isolator
2
+ Copyright 2026 Inworld AI
3
+
4
+ The model weights were trained on Inworld's first-party data, including data
5
+ purchased from vendors under private terms, and on these third-party datasets:
6
+
7
+ - VocalSet — CC BY 4.0, https://zenodo.org/records/1442513
8
+ - IndicVoices-R — CC BY 4.0,
9
+ https://huggingface.co/datasets/ai4bharat/indicvoices_r
10
+ - VCTK — ODC-By 1.0, https://datashare.ed.ac.uk/handle/10283/2119
11
+
12
+ This product optionally downloads and uses, at runtime, third-party models and
13
+ libraries that remain under their own licenses:
14
+
15
+ - Mamba selective-scan kernels (mamba-ssm, causal-conv1d) — Apache-2.0,
16
+ https://github.com/state-spaces/mamba (optional [fast] extra; without it
17
+ the same scan runs in plain PyTorch).
18
+
19
+ The golden parity fixtures include a modified LibriSpeech recording under
20
+ CC BY 4.0; see tests/fixtures/README.md. They are not included in the Python
21
+ package.
README.md ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: inworld-voice-isolation
4
+ pipeline_tag: audio-to-audio
5
+ tags: [audio, speech, speech-enhancement, speech-denoising, noise-suppression, voice-isolation, 48khz, full-band, streaming, realtime]
6
+ ---
7
+
8
+ <p align="center">
9
+ <picture>
10
+ <source media="(prefers-color-scheme: dark)" srcset="https://huggingface.co/inworld/voice-isolator/resolve/main/docs/assets/inworld-logo-white.svg">
11
+ <img src="https://huggingface.co/inworld/voice-isolator/resolve/main/docs/assets/inworld-logo-black.svg" alt="Inworld" width="220">
12
+ </picture>
13
+ </p>
14
+
15
+ <h1 align="center">Voice Isolator</h1>
16
+
17
+ <p align="center">
18
+ Open-license (Apache-2.0) 48 kHz voice isolation for noisy speech recordings and live audio.
19
+ </p>
20
+
21
+ <p align="center">
22
+ <a href="https://github.com/inworld-ai/voice-isolator"><img src="https://img.shields.io/badge/GitHub-inworld--ai%2Fvoice--isolator-181717?logo=github" alt="GitHub: inworld-ai/voice-isolator"></a>
23
+ </p>
24
+
25
+ ---
26
+
27
+ ## TL;DR
28
+
29
+ Inworld Voice Isolator v1 ships as two models that share one architecture:
30
+
31
+ | | `voice-isolator-v1` | `voice-isolator-v1-realtime` |
32
+ |---|---|---|
33
+ | made for | recorded audio and anything not latency-sensitive, at the best quality | live audio, as a stream in your pipeline or production |
34
+ | how it runs | offline: every frame sees its whole 8 s chunk | a causal stream with 20 ms of look-ahead |
35
+ | parameters | 64M | 58M |
36
+
37
+ **Use them for** cleaning recordings before playback or publication, curating speech datasets and voice pipelines where the speaker's identity must survive.
38
+ With the realtime model, use them for live calls and streams.
39
+ Subtract the isolated voice from the input to extract background noise or a backing-track residual for vocals/music separation.
40
+
41
+ **They are not** a speaker selector or a restoration model.
42
+ Restoration is planned for version 2 (see [Plans](https://github.com/inworld-ai/voice-isolator#plans)).
43
+
44
+ ## Quick start
45
+
46
+ Using a coding agent? Point it at the [setup section of AGENTS.md](https://github.com/inworld-ai/voice-isolator/blob/main/AGENTS.md#setting-up-the-voice-isolator-for-a-user): it installs the package, checks the machine with `voice-isolate-doctor` and cleans a first file.
47
+
48
+ ```bash
49
+ pip install inworld-voice-isolation
50
+ # or from a clone: git clone https://github.com/inworld-ai/voice-isolator && cd voice-isolator && pip install -e .
51
+
52
+ # a noisy example; a clone also has it at demo/examples/sample_14.wav
53
+ curl -LO https://raw.githubusercontent.com/inworld-ai/voice-isolator/main/demo/examples/sample_14.wav
54
+
55
+ # offline isolation (downloads the offline model on first use):
56
+ # the voice goes to sample_14_clean.wav and the removed background
57
+ # to sample_14_clean_background.wav, beside it
58
+ voice-isolate sample_14.wav sample_14_clean.wav
59
+ ```
60
+
61
+ Both are float32 WAVs at 48 kHz, with their original levels preserved; together they reconstruct the aligned mono input.
62
+ Use `--output-sr 0` to keep the input rate, `--background noise.wav` to choose the background path for one file, or `--no-background` to save only the voice.
63
+
64
+ ```python
65
+ from inworld import voice_isolation
66
+
67
+ # isolate a recording offline
68
+ offline = voice_isolation.VoiceIsolator("inworld/voice-isolator")
69
+ wav, sample_rate = voice_isolation.load_audio("sample_14.wav")
70
+ voice = offline.isolate(wav, sample_rate)
71
+ voice_isolation.save_audio("sample_14_clean.wav", voice, sample_rate, subtype="FLOAT")
72
+ voice_isolation.save_audio("sample_14_clean_background.wav", wav - voice, sample_rate, subtype="FLOAT") # what was removed
73
+ ```
74
+
75
+ ### Streaming
76
+
77
+ The realtime model isolates the voice as the audio arrives, with 20 ms of look-ahead:
78
+
79
+ ```python
80
+ import torch
81
+ from inworld import voice_isolation
82
+
83
+ live = voice_isolation.VoiceIsolator("inworld/voice-isolator",
84
+ mode="streaming", lookahead_frames=2)
85
+ session = live.stream() # takes 48 kHz mono, in pieces of any size
86
+ wav, sample_rate = voice_isolation.load_audio("sample_14.wav") # 48 kHz mono, standing in for a live source
87
+ voice = []
88
+ for start in range(0, len(wav), 960): # 20 ms at a time, as a microphone delivers it
89
+ voice.append(session.push(wav[start:start + 960])) # the samples that are final: play or send them
90
+ voice.append(session.flush()) # the rest, once the source ends
91
+ voice_isolation.save_audio("sample_14_streamed.wav", torch.cat(voice), sample_rate)
92
+ ```
93
+
94
+ The streaming CLI writes only the isolated voice, after the whole file has gone through:
95
+
96
+ ```bash
97
+ voice-isolate sample_14.wav sample_14_streamed.wav --mode streaming --lookahead 2
98
+ ```
99
+
100
+ The weights download on first use, and their checksums are verified.
101
+ The mode picks the checkpoint: `voice-isolator-v1` offline, `voice-isolator-v1-realtime` for streaming.
102
+ CUDA is used when available, Apple's Metal backend (`mps`) on an Apple-silicon Mac with PyTorch 2.6 or later, and the CPU otherwise; `--device` picks one.
103
+
104
+ The code, the [interactive demo](https://github.com/inworld-ai/voice-isolator/blob/main/demo/README.md) and the [benchmark](https://github.com/inworld-ai/voice-isolator/blob/main/bench/README.md) are on GitHub: [inworld-ai/voice-isolator](https://github.com/inworld-ai/voice-isolator).
105
+ The demo loads both models at startup: **Offline** processes files and samples into voice and background audio; **Online** streams the microphone for up to 60 seconds with updating waveforms and spectrograms, pausing capture before playback.
106
+
107
+ ## Hardware
108
+
109
+ Tested on NVIDIA Ampere, Hopper and Blackwell GPUs (A100, H100, B200 and B300) and on CPU.
110
+ Smaller GPUs are not tested yet (see [Plans](https://github.com/inworld-ai/voice-isolator#plans)).
111
+
112
+ ## The VIBE benchmark
113
+
114
+ <p align="center">
115
+ <picture>
116
+ <source media="(prefers-color-scheme: dark)" srcset="https://huggingface.co/inworld/voice-isolator/resolve/main/docs/assets/board-dark.svg">
117
+ <img src="https://huggingface.co/inworld/voice-isolator/resolve/main/docs/assets/board-light.svg" alt="Inworld VIBE full-band tier: denoising score per system" width="100%">
118
+ </picture>
119
+ </p>
120
+
121
+ Inworld VIBE (Voice Isolation Benchmark and Evals) ranks 48 kHz voice isolators on two boards.
122
+ The chart is the denoising board, which ranks every system except those that put more than 10 dB more energy above a band-limited input's band than inside it; those are ranked on restoration.
123
+ Inworld scores every system on its internal evaluation set, which is not distributed.
124
+
125
+ [How the systems are scored and what the scores mean](https://github.com/inworld-ai/voice-isolator/blob/main/bench/README.md).
126
+
127
+ ## Architecture
128
+
129
+ <p align="center">
130
+ <picture>
131
+ <source media="(prefers-color-scheme: dark)" srcset="https://huggingface.co/inworld/voice-isolator/resolve/main/docs/assets/architecture-dark.svg">
132
+ <img src="https://huggingface.co/inworld/voice-isolator/resolve/main/docs/assets/architecture-light.svg" alt="The network: STFT, band split, seven dual-path blocks, per-band heads, iSTFT; the two checkpoints" width="100%">
133
+ </picture>
134
+ </p>
135
+
136
+ A band-split dual-path network over the STFT (n_fft 2048, hop 480 at 48 kHz, 10 ms frames).
137
+ Each frame's spectrum is cut into 46 bands, narrow at low frequency and wide at the top, one token per band and frame, width 512.
138
+ Seven blocks refine the tokens, alternating two kinds.
139
+ Four blocks run time attention with rotary position and exclusive self attention, followed by attention across bands.
140
+ Three blocks run Mamba along time, followed by Mamba across bands (state 16).
141
+ Per-band heads produce a bounded complex mask and a bounded per-bin residual, added to the input spectrum.
142
+ The offline model has 64.0M parameters.
143
+ The realtime model has 58.2M; its blocks are causal and it carries a look-ahead embedding.
144
+ Input is one channel at 48 kHz; nothing is separated or synthesized beforehand.
145
+
146
+ ## Two checkpoints
147
+
148
+ The offline model, `voice-isolator-v1`, is two-sided: every frame sees its whole 8 s chunk, and long inputs render in 8 s chunks overlapping by 2 s.
149
+ The realtime model, `voice-isolator-v1-realtime`, is causal, with a trained look-ahead of 0, 20 or 40 ms; its algorithmic latency is 63 ms at 20 ms of look-ahead.
150
+ Both keep the foreground voice: when two people speak at once, the louder voice is kept and one a few dB quieter is removed, while voices at similar levels are usually both kept.
151
+ In the speech-enhancement literature, version 1 does denoising (noise suppression): it removes what surrounds the voice and restores nothing the recording lost, such as missing bandwidth; restoration comes with version 2.
152
+
153
+ ## Training data
154
+
155
+ Inworld Voice Isolator v1 was trained on approximately 10,000 hours of unique audio.
156
+ Paired examples built from recorded speech: read and conversational speech in many languages, expressive and character voices, whispered speech, singing, and the speaker's own non-verbal sounds such as laughter, breaths and sighs.
157
+ The speech was mixed with environmental and household noise, traffic, rain and wind, music and crowd sound, isolated transient events and competing talkers, through measured and simulated room responses and telephony and codec degradations.
158
+ Real recordings of the same speech, captured clean and in rooms, complete the set.
159
+ The objective: return the voice as it was recorded, remove everything that is not the speaker (noise, music, other voices and the late room tail), keep the speaker's own non-verbal sounds, level and timing, and invent nothing.
160
+
161
+ Third-party datasets used in training are credited in [NOTICE](NOTICE).
162
+
163
+ ## License
164
+
165
+ Code and weights are Apache-2.0 ([LICENSE](LICENSE)).
166
+ Third-party notices are in [NOTICE](NOTICE).
167
+
168
+ ## How to contribute
169
+
170
+ Everyone is welcome to use the model however they like and to make it better in any way they see fit!
171
+ Development happens on GitHub: see [CONTRIBUTING.md](https://github.com/inworld-ai/voice-isolator/blob/main/CONTRIBUTING.md) for setup, tests and bug reports.
172
+
173
+ ---
174
+
175
+ <p align="center">Built for people with ❤️ by Inworld.</p>
denoiser.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:647335a6aeb4dc706b895532c209d51e0e84a4849d17b339f00d4392a050ae53
3
+ size 256260128
denoiser_realtime.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76598f05523c0669e76562a8b2f31c9d395fca316e80c907ee11775e7497ae0f
3
+ size 232780800
docs/assets/architecture-dark.svg ADDED
docs/assets/architecture-light.svg ADDED
docs/assets/board-dark.svg ADDED
docs/assets/board-light.svg ADDED
docs/assets/inworld-logo-black.svg ADDED
docs/assets/inworld-logo-white.svg ADDED