Upload folder using huggingface_hub
Browse files- LICENSE +201 -0
- README.md +279 -0
- config.json +132 -0
- inference.py +241 -0
- inventory.json +211 -0
- lexicon.json +1 -0
- onnx/tiny-swara-int8.onnx +3 -0
- tiny-bn.onnx → onnx/tiny-swara.onnx +1 -1
- requirements.txt +2 -0
- samples/bf-1.mp3 +0 -0
- samples/bf-2.mp3 +0 -0
- samples/bf-3.mp3 +0 -0
- samples/bf-4.mp3 +0 -0
- samples/bf-5.mp3 +0 -0
- samples/bm-1.mp3 +0 -0
- samples/bm-2.mp3 +0 -0
- samples/bm-3.mp3 +0 -0
- samples/bm-4.mp3 +0 -0
- samples/bm-5.mp3 +0 -0
- samples/int8-code-mixed.mp3 +0 -0
- samples/int8-female.mp3 +0 -0
- samples/int8-male.mp3 +0 -0
- tiny_voca/__init__.py +4 -0
- tiny_voca/text.py +352 -0
LICENSE
ADDED
|
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Apache License
|
| 2 |
+
Version 2.0, January 2004
|
| 3 |
+
http://www.apache.org/licenses/
|
| 4 |
+
|
| 5 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
| 6 |
+
|
| 7 |
+
1. Definitions.
|
| 8 |
+
|
| 9 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
| 10 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
| 11 |
+
|
| 12 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
| 13 |
+
the copyright owner that is granting the License.
|
| 14 |
+
|
| 15 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
| 16 |
+
other entities that control, are controlled by, or are under common
|
| 17 |
+
control with that entity. For the purposes of this definition,
|
| 18 |
+
"control" means (i) the power, direct or indirect, to cause the
|
| 19 |
+
direction or management of such entity, whether by contract or
|
| 20 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
| 21 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
| 22 |
+
|
| 23 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
| 24 |
+
exercising permissions granted by this License.
|
| 25 |
+
|
| 26 |
+
"Source" form shall mean the preferred form for making modifications,
|
| 27 |
+
including but not limited to software source code, documentation
|
| 28 |
+
source, and configuration files.
|
| 29 |
+
|
| 30 |
+
"Object" form shall mean any form resulting from mechanical
|
| 31 |
+
transformation or translation of a Source form, including but
|
| 32 |
+
not limited to compiled object code, generated documentation,
|
| 33 |
+
and conversions to other media types.
|
| 34 |
+
|
| 35 |
+
"Work" shall mean the work of authorship, whether in Source or
|
| 36 |
+
Object form, made available under the License, as indicated by a
|
| 37 |
+
copyright notice that is included in or attached to the work
|
| 38 |
+
(an example is provided in the Appendix below).
|
| 39 |
+
|
| 40 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
| 41 |
+
form, that is based on (or derived from) the Work and for which the
|
| 42 |
+
editorial revisions, annotations, elaborations, or other modifications
|
| 43 |
+
represent, as a whole, an original work of authorship. For the purposes
|
| 44 |
+
of this License, Derivative Works shall not include works that remain
|
| 45 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
| 46 |
+
the Work and Derivative Works thereof.
|
| 47 |
+
|
| 48 |
+
"Contribution" shall mean any work of authorship, including
|
| 49 |
+
the original version of the Work and any modifications or additions
|
| 50 |
+
to that Work or Derivative Works thereof, that is intentionally
|
| 51 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
| 52 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
| 53 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
| 54 |
+
means any form of electronic, verbal, or written communication sent
|
| 55 |
+
to the Licensor or its representatives, including but not limited to
|
| 56 |
+
communication on electronic mailing lists, source code control systems,
|
| 57 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
| 58 |
+
Licensor for the purpose of discussing and improving the Work, but
|
| 59 |
+
excluding communication that is conspicuously marked or otherwise
|
| 60 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
| 61 |
+
|
| 62 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
| 63 |
+
on behalf of whom a Contribution has been received by Licensor and
|
| 64 |
+
subsequently incorporated within the Work.
|
| 65 |
+
|
| 66 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
| 67 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 68 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 69 |
+
copyright license to reproduce, prepare Derivative Works of,
|
| 70 |
+
publicly display, publicly perform, sublicense, and distribute the
|
| 71 |
+
Work and such Derivative Works in Source or Object form.
|
| 72 |
+
|
| 73 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
| 74 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 75 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 76 |
+
(except as stated in this section) patent license to make, have made,
|
| 77 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
| 78 |
+
where such license applies only to those patent claims licensable
|
| 79 |
+
by such Contributor that are necessarily infringed by their
|
| 80 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
| 81 |
+
with the Work to which such Contribution(s) was submitted. If You
|
| 82 |
+
institute patent litigation against any entity (including a
|
| 83 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
| 84 |
+
or a Contribution incorporated within the Work constitutes direct
|
| 85 |
+
or contributory patent infringement, then any patent licenses
|
| 86 |
+
granted to You under this License for that Work shall terminate
|
| 87 |
+
as of the date such litigation is filed.
|
| 88 |
+
|
| 89 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
| 90 |
+
Work or Derivative Works thereof in any medium, with or without
|
| 91 |
+
modifications, and in Source or Object form, provided that You
|
| 92 |
+
meet the following conditions:
|
| 93 |
+
|
| 94 |
+
(a) You must give any other recipients of the Work or
|
| 95 |
+
Derivative Works a copy of this License; and
|
| 96 |
+
|
| 97 |
+
(b) You must cause any modified files to carry prominent notices
|
| 98 |
+
stating that You changed the files; and
|
| 99 |
+
|
| 100 |
+
(c) You must retain, in the Source form of any Derivative Works
|
| 101 |
+
that You distribute, all copyright, patent, trademark, and
|
| 102 |
+
attribution notices from the Source form of the Work,
|
| 103 |
+
excluding those notices that do not pertain to any part of
|
| 104 |
+
the Derivative Works; and
|
| 105 |
+
|
| 106 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
| 107 |
+
distribution, then any Derivative Works that You distribute must
|
| 108 |
+
include a readable copy of the attribution notices contained
|
| 109 |
+
within such NOTICE file, excluding those notices that do not
|
| 110 |
+
pertain to any part of the Derivative Works, in at least one
|
| 111 |
+
of the following places: within a NOTICE text file distributed
|
| 112 |
+
as part of the Derivative Works; within the Source form or
|
| 113 |
+
documentation, if provided along with the Derivative Works; or,
|
| 114 |
+
within a display generated by the Derivative Works, if and
|
| 115 |
+
wherever such third-party notices normally appear. The contents
|
| 116 |
+
of the NOTICE file are for informational purposes only and
|
| 117 |
+
do not modify the License. You may add Your own attribution
|
| 118 |
+
notices within Derivative Works that You distribute, alongside
|
| 119 |
+
or as an addendum to the NOTICE text from the Work, provided
|
| 120 |
+
that such additional attribution notices cannot be construed
|
| 121 |
+
as modifying the License.
|
| 122 |
+
|
| 123 |
+
You may add Your own copyright statement to Your modifications and
|
| 124 |
+
may provide additional or different license terms and conditions
|
| 125 |
+
for use, reproduction, or distribution of Your modifications, or
|
| 126 |
+
for any such Derivative Works as a whole, provided Your use,
|
| 127 |
+
reproduction, and distribution of the Work otherwise complies with
|
| 128 |
+
the conditions stated in this License.
|
| 129 |
+
|
| 130 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
| 131 |
+
any Contribution intentionally submitted for inclusion in the Work
|
| 132 |
+
by You to the Licensor shall be under the terms and conditions of
|
| 133 |
+
this License, without any additional terms or conditions.
|
| 134 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
| 135 |
+
the terms of any separate license agreement you may have executed
|
| 136 |
+
with Licensor regarding such Contributions.
|
| 137 |
+
|
| 138 |
+
6. Trademarks. This License does not grant permission to use the trade
|
| 139 |
+
names, trademarks, service marks, or product names of the Licensor,
|
| 140 |
+
except as required for reasonable and customary use in describing the
|
| 141 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
| 142 |
+
|
| 143 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
| 144 |
+
agreed to in writing, Licensor provides the Work (and each
|
| 145 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
| 146 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
| 147 |
+
implied, including, without limitation, any warranties or conditions
|
| 148 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
| 149 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
| 150 |
+
appropriateness of using or redistributing the Work and assume any
|
| 151 |
+
risks associated with Your exercise of permissions under this License.
|
| 152 |
+
|
| 153 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
| 154 |
+
whether in tort (including negligence), contract, or otherwise,
|
| 155 |
+
unless required by applicable law (such as deliberate and grossly
|
| 156 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
| 157 |
+
liable to You for damages, including any direct, indirect, special,
|
| 158 |
+
incidental, or consequential damages of any character arising as a
|
| 159 |
+
result of this License or out of the use or inability to use the
|
| 160 |
+
Work (including but not limited to damages for loss of goodwill,
|
| 161 |
+
work stoppage, computer failure or malfunction, or any and all
|
| 162 |
+
other commercial damages or losses), even if such Contributor
|
| 163 |
+
has been advised of the possibility of such damages.
|
| 164 |
+
|
| 165 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
| 166 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
| 167 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
| 168 |
+
or other liability obligations and/or rights consistent with this
|
| 169 |
+
License. However, in accepting such obligations, You may act only
|
| 170 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
| 171 |
+
of any other Contributor, and only if You agree to indemnify,
|
| 172 |
+
defend, and hold each Contributor harmless for any liability
|
| 173 |
+
incurred by, or claims asserted against, such Contributor by reason
|
| 174 |
+
of your accepting any such warranty or additional liability.
|
| 175 |
+
|
| 176 |
+
END OF TERMS AND CONDITIONS
|
| 177 |
+
|
| 178 |
+
APPENDIX: How to apply the Apache License to your work.
|
| 179 |
+
|
| 180 |
+
To apply the Apache License to your work, attach the following
|
| 181 |
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
| 182 |
+
replaced with your own identifying information. (Don't include
|
| 183 |
+
the brackets!) The text should be enclosed in the appropriate
|
| 184 |
+
comment syntax for the file format. We also recommend that a
|
| 185 |
+
file or class name and description of purpose be included on the
|
| 186 |
+
same "printed page" as the copyright notice for easier
|
| 187 |
+
identification within third-party archives.
|
| 188 |
+
|
| 189 |
+
Copyright 2026 Xeven7
|
| 190 |
+
|
| 191 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
| 192 |
+
you may not use this file except in compliance with the License.
|
| 193 |
+
You may obtain a copy of the License at
|
| 194 |
+
|
| 195 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
| 196 |
+
|
| 197 |
+
Unless required by applicable law or agreed to in writing, software
|
| 198 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
| 199 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 200 |
+
See the License for the specific language governing permissions and
|
| 201 |
+
limitations under the License.
|
README.md
CHANGED
|
@@ -1,3 +1,282 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- bn
|
| 5 |
+
- en
|
| 6 |
+
pipeline_tag: text-to-speech
|
| 7 |
+
tags:
|
| 8 |
+
- text-to-speech
|
| 9 |
+
- onnx
|
| 10 |
+
- bengali
|
| 11 |
+
- onnxruntime
|
| 12 |
+
- tiny
|
| 13 |
+
datasets:
|
| 14 |
+
- ai4bharat/Rasa
|
| 15 |
---
|
| 16 |
+
|
| 17 |
+
# tiny-swara
|
| 18 |
+
|
| 19 |
+
**tiny-swara** is a tiny, absurdly fast Bengali text-to-speech model with two
|
| 20 |
+
voices, **BF** (female) and **BM** (male).
|
| 21 |
+
|
| 22 |
+
It packs the entire pipeline — phoneme encoder, duration predictor, prosody
|
| 23 |
+
stacks and a source-filter waveform generator — into **4.5M parameters and an
|
| 24 |
+
8.2 MiB INT8 file**. On just **2 CPU threads** it renders **4.75 seconds of
|
| 25 |
+
speech in 103 ms: 45.9× faster than real time**, with about 4.6 seconds of
|
| 26 |
+
headroom before playback even catches up. No GPU. No cloud. No waiting.
|
| 27 |
+
|
| 28 |
+
Built on the [tiny-voca](https://huggingface.co/n4ze3m/tiny-voca) architecture,
|
| 29 |
+
with a source-filter waveform generator instead of a neural vocoder.
|
| 30 |
+
|
| 31 |
+
<audio controls src="https://huggingface.co/Xeven7/tiny-swara/resolve/main/samples/int8-female.mp3"></audio>
|
| 32 |
+
|
| 33 |
+
| | |
|
| 34 |
+
| ----------------- | ---------------------------------------------- |
|
| 35 |
+
| Parameters | 4,537,483 |
|
| 36 |
+
| Voices | BF, BM (Bengali) |
|
| 37 |
+
| Input | Bengali text, phonemized with espeak-ng (`bn`) |
|
| 38 |
+
| Output | 24 kHz mono |
|
| 39 |
+
| Format | ONNX (opset 17) |
|
| 40 |
+
| Recommended model | `onnx/tiny-swara-int8.onnx` |
|
| 41 |
+
| License | Apache-2.0 |
|
| 42 |
+
|
| 43 |
+
## Files
|
| 44 |
+
|
| 45 |
+
| File | Size | Contents |
|
| 46 |
+
| --------------------------- | -------: | ---------------------------------------------------- |
|
| 47 |
+
| `onnx/tiny-swara-int8.onnx` | 8.24 MiB | INT8-quantized model, recommended |
|
| 48 |
+
| `onnx/tiny-swara.onnx` | 20.4 MiB | FP32 model, reference |
|
| 49 |
+
| `config.json` | | Model settings, phoneme vocabulary, voices |
|
| 50 |
+
| `inventory.json` | | Phoneme inventory and fallback mappings |
|
| 51 |
+
| `lexicon.json` | | English-to-Bengali word mappings for code-mixed text |
|
| 52 |
+
| `tiny_voca/text.py` | | Bengali-patched frontend: text to phoneme tokens |
|
| 53 |
+
| `tiny_voca/__init__.py` | | Package marker |
|
| 54 |
+
| `inference.py` | | ONNX inference, CLI and Python API |
|
| 55 |
+
| `requirements.txt` | | Python dependencies |
|
| 56 |
+
| `samples/` | | MP3 samples used on this page (64 kbps mono) |
|
| 57 |
+
|
| 58 |
+
SHA256:
|
| 59 |
+
|
| 60 |
+
- `onnx/tiny-swara.onnx`: `cef829cff4b6cb38554e32d8f96b9b51f96a4c0e9cb2e406b53ac79d5923d630`
|
| 61 |
+
- `onnx/tiny-swara-int8.onnx`: `f3080233715cf22ebf519cfc1f81a8ebe4c937c0cdce0285b2cf51998c64eabb`
|
| 62 |
+
|
| 63 |
+
## Samples
|
| 64 |
+
|
| 65 |
+
The first table uses recordings exported from the notebook. The second table was
|
| 66 |
+
generated with the packaged `inference.py` and the INT8 model, so it also serves
|
| 67 |
+
as an INT8 check. All files here are MP3 at 64 kbps mono to keep the repository
|
| 68 |
+
small; the model itself outputs 24 kHz mono WAV.
|
| 69 |
+
|
| 70 |
+
### Female (BF) and male (BM)
|
| 71 |
+
|
| 72 |
+
| Text | Female (BF) | Male (BM) |
|
| 73 |
+
| ----------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------- |
|
| 74 |
+
| আমার order কোথায়? | <audio controls preload="none" src="https://huggingface.co/Xeven7/tiny-swara/resolve/main/samples/bf-1.mp3"></audio> | <audio controls preload="none" src="https://huggingface.co/Xeven7/tiny-swara/resolve/main/samples/bm-1.mp3"></audio> |
|
| 75 |
+
| গতকাল আমি খুব ব্যস্ত ছিলাম, তাই সন্ধ্যায় তোমাকে ফোন করতে পারিনি। | <audio controls preload="none" src="https://huggingface.co/Xeven7/tiny-swara/resolve/main/samples/bf-2.mp3"></audio> | <audio controls preload="none" src="https://huggingface.co/Xeven7/tiny-swara/resolve/main/samples/bm-2.mp3"></audio> |
|
| 76 |
+
| Hello বন্ধুরা, আপনারা কেমন আছেন? | <audio controls preload="none" src="https://huggingface.co/Xeven7/tiny-swara/resolve/main/samples/bf-3.mp3"></audio> | <audio controls preload="none" src="https://huggingface.co/Xeven7/tiny-swara/resolve/main/samples/bm-3.mp3"></audio> |
|
| 77 |
+
| বাহ, এই ছোট মডেলটি তো দারুণ! আমি মুগ্ধ। | <audio controls preload="none" src="https://huggingface.co/Xeven7/tiny-swara/resolve/main/samples/bf-4.mp3"></audio> | <audio controls preload="none" src="https://huggingface.co/Xeven7/tiny-swara/resolve/main/samples/bm-4.mp3"></audio> |
|
| 78 |
+
| আমি তোমাকে পছন্দ করি। | <audio controls preload="none" src="https://huggingface.co/Xeven7/tiny-swara/resolve/main/samples/bf-5.mp3"></audio> | <audio controls preload="none" src="https://huggingface.co/Xeven7/tiny-swara/resolve/main/samples/bm-5.mp3"></audio> |
|
| 79 |
+
|
| 80 |
+
### INT8 model
|
| 81 |
+
|
| 82 |
+
| Text | Voice | Audio |
|
| 83 |
+
| ----------------------------------------------------------- | ----- | ------------------------------------------------------------------------------------------------------------------------------- |
|
| 84 |
+
| আমার সোনার বাংলা, আমি তোমায় ভালোবাসি। | BF | <audio controls preload="none" src="https://huggingface.co/Xeven7/tiny-swara/resolve/main/samples/int8-female.mp3"></audio> |
|
| 85 |
+
| আজকের তারিখ ২০ নভেম্বর ২০২৬, তাপমাত্রা ৩২ ডিগ্রি সেলসিয়াস। | BM | <audio controls preload="none" src="https://huggingface.co/Xeven7/tiny-swara/resolve/main/samples/int8-male.mp3"></audio> |
|
| 86 |
+
| Hello, আমি আপনার order টি confirm করেছি। | BF | <audio controls preload="none" src="https://huggingface.co/Xeven7/tiny-swara/resolve/main/samples/int8-code-mixed.mp3"></audio> |
|
| 87 |
+
|
| 88 |
+
## Usage
|
| 89 |
+
|
| 90 |
+
### Python script
|
| 91 |
+
|
| 92 |
+
```bash
|
| 93 |
+
pip install -r requirements.txt
|
| 94 |
+
sudo apt install espeak-ng # or: brew install espeak-ng
|
| 95 |
+
|
| 96 |
+
python inference.py \
|
| 97 |
+
--text "আমি ভালো আছি, আপনার অর্ডার কনফার্ম হয়েছে।" \
|
| 98 |
+
--voice BF \
|
| 99 |
+
--output hello.wav
|
| 100 |
+
```
|
| 101 |
+
|
| 102 |
+
| Option | Default | Meaning |
|
| 103 |
+
| --------------- | --------------------------- | ----------------------------------------------- |
|
| 104 |
+
| `--text` | | Text to speak |
|
| 105 |
+
| `--text-file` | | Read the text from a file instead of `--text` |
|
| 106 |
+
| `--voice` | `BF` | `BF` (female) or `BM` (male) |
|
| 107 |
+
| `--output` | `tiny-swara.wav` | Output WAV path |
|
| 108 |
+
| `--model` | `onnx/tiny-swara-int8.onnx` | Path to an ONNX file |
|
| 109 |
+
| `--speed` | `1.0` | Speaking rate; larger is faster |
|
| 110 |
+
| `--pitch-shift` | `0.0` | Added to log F0; 0.058 is about one semitone |
|
| 111 |
+
| `--pitch-range` | `1.0` | Scales pitch movement around the utterance mean |
|
| 112 |
+
|
| 113 |
+
Text is read one sentence at a time, so text of any length works. Output is
|
| 114 |
+
peak-normalized to 0.9 before it is written.
|
| 115 |
+
|
| 116 |
+
### Python API
|
| 117 |
+
|
| 118 |
+
```python
|
| 119 |
+
from inference import TinySwara
|
| 120 |
+
|
| 121 |
+
tts = TinySwara(voice="BF") # INT8 model by default
|
| 122 |
+
tts.save("আমি ভালো আছি।", "hello.wav")
|
| 123 |
+
|
| 124 |
+
# Sentence-level streaming: each chunk is complete before it is yielded.
|
| 125 |
+
for audio in tts.stream("প্রথম বাক্য। দ্বিতীয় বাক্য।"):
|
| 126 |
+
play(audio) # float32 mono at 24 kHz
|
| 127 |
+
```
|
| 128 |
+
|
| 129 |
+
`inference.py` sets `TINY_VOCA_INVENTORY`, `TINY_VOCA_LEXICON` and
|
| 130 |
+
`TINY_VOCA_FRONTEND` before importing `tiny_voca.text`, so the patched frontend
|
| 131 |
+
is wired up automatically. The frontend must be the Bengali-patched version
|
| 132 |
+
shipped here; the upstream tiny-voca `text.py` has no Bengali lexicon support.
|
| 133 |
+
|
| 134 |
+
### ONNX directly
|
| 135 |
+
|
| 136 |
+
The graph takes phoneme ids and stress values; text is converted to ids outside
|
| 137 |
+
the graph by `tiny_voca/text.py`. The ids are the positions in `vocab` in
|
| 138 |
+
`config.json`.
|
| 139 |
+
|
| 140 |
+
```python
|
| 141 |
+
import numpy as np
|
| 142 |
+
import onnxruntime as ort
|
| 143 |
+
|
| 144 |
+
session = ort.InferenceSession("onnx/tiny-swara-int8.onnx")
|
| 145 |
+
one = lambda value: np.array([value], dtype=np.float32)
|
| 146 |
+
|
| 147 |
+
audio, durations = session.run(None, {
|
| 148 |
+
"tokens": np.array([[1, 62, 23, 64, 6, 2]], dtype=np.int64), # <bos> ami . <eos>
|
| 149 |
+
"stress": np.array([[0, 1, 0, 0, 0, 0]], dtype=np.int64),
|
| 150 |
+
"voice": np.array([0], dtype=np.int64), # 0 = BF, 1 = BM
|
| 151 |
+
"speed": one(1.0),
|
| 152 |
+
"pitch_shift": one(0.0),
|
| 153 |
+
"pitch_range": one(1.0),
|
| 154 |
+
})
|
| 155 |
+
```
|
| 156 |
+
|
| 157 |
+
| Input | Type | Shape | Meaning |
|
| 158 |
+
| ------------- | ------- | ------ | ------------------------------------------ |
|
| 159 |
+
| `tokens` | int64 | [1, N] | Phoneme ids, including `<bos>` and `<eos>` |
|
| 160 |
+
| `stress` | int64 | [1, N] | 0 none, 1 primary, 2 secondary |
|
| 161 |
+
| `voice` | int64 | [1] | 0 = BF, 1 = BM |
|
| 162 |
+
| `speed` | float32 | [1] | 1.0 as predicted; larger is faster |
|
| 163 |
+
| `pitch_shift` | float32 | [1] | Added to log F0 |
|
| 164 |
+
| `pitch_range` | float32 | [1] | Scales pitch movement |
|
| 165 |
+
|
| 166 |
+
| Output | Type | Shape | Meaning |
|
| 167 |
+
| ----------- | ------- | ------------ | --------------------------------------------- |
|
| 168 |
+
| `audio` | float32 | [1, samples] | Waveform at 24 kHz |
|
| 169 |
+
| `durations` | int64 | [1, N] | Length of each token in frames of 256 samples |
|
| 170 |
+
|
| 171 |
+
The model reads one utterance per call, up to 512 tokens and 32 seconds. Split
|
| 172 |
+
longer text into sentences. The raw graph output can be quiet, so scale it to a
|
| 173 |
+
usable level before saving 16-bit samples:
|
| 174 |
+
|
| 175 |
+
```python
|
| 176 |
+
audio = audio[0]
|
| 177 |
+
audio *= 0.9 / np.abs(audio).max()
|
| 178 |
+
```
|
| 179 |
+
|
| 180 |
+
## Model
|
| 181 |
+
|
| 182 |
+
Text is converted to phonemes with [espeak-ng](https://github.com/espeak-ng/espeak-ng)
|
| 183 |
+
(`-v bn --ipa`) by `tiny_voca/text.py` and mapped onto a Bengali phoneme
|
| 184 |
+
inventory. Phonemes that are not in the inventory are rewritten with the
|
| 185 |
+
fallback rules in `inventory.json`. Known English words in code-mixed text are
|
| 186 |
+
replaced with their Bengali spelling using `lexicon.json`; other Latin words are
|
| 187 |
+
phonemized with the English (`en-us`) voice and mapped back through the same
|
| 188 |
+
fallbacks. The token stream matches training: `<bos>`, `<sp>` between words,
|
| 189 |
+
explicit punctuation tokens, and `<eos>`.
|
| 190 |
+
|
| 191 |
+
A transformer encoder (4 blocks) reads the phonemes and a duration predictor
|
| 192 |
+
gives each one a length in frames. Two frame-level transformer stacks (2 and 5
|
| 193 |
+
blocks) predict pitch, voicing and energy and then the parameters of the
|
| 194 |
+
waveform generator. All blocks use 192 channels, 4 heads and rotary position
|
| 195 |
+
embeddings. The waveform is produced by a source-filter synthesizer instead of a
|
| 196 |
+
neural vocoder: a band-limited pulse train at the predicted pitch and a noise
|
| 197 |
+
signal are each shaped by a time-varying filter predicted once per frame
|
| 198 |
+
(256 samples, 10.7 ms).
|
| 199 |
+
|
| 200 |
+
| | |
|
| 201 |
+
| -------------- | ------------------------------------------------------------- |
|
| 202 |
+
| Vocabulary | 77 tokens (Bengali IPA phonemes, punctuation, special tokens) |
|
| 203 |
+
| Encoder | 4 blocks, 192 channels, 4 heads |
|
| 204 |
+
| Frame stacks | 2 + 5 blocks, 192 channels, 4 heads |
|
| 205 |
+
| Waveform | Source-filter, hop 256 |
|
| 206 |
+
| Training steps | 60,000 |
|
| 207 |
+
|
| 208 |
+
## Training
|
| 209 |
+
|
| 210 |
+
| | |
|
| 211 |
+
|---|---|
|
| 212 |
+
| Dataset | [ai4bharat/Rasa](https://huggingface.co/datasets/ai4bharat/Rasa), Bengali subset, styles WIKI, CONV, BOOK, NEWS, SANGRAH, INDIC |
|
| 213 |
+
| Hours / clips | 11.5 h, 6,275 train / 112 validation / 61 test clips after filtering |
|
| 214 |
+
| Steps | 60,000 |
|
| 215 |
+
| Hardware | 1 × Tesla T4 on Kaggle, in two sessions (about 10.5 h and 7 h) |
|
| 216 |
+
| Alignment | `facebook/wav2vec2-lv-60-espeak-cv-ft`, relaxed gates (weak-phone fraction 0.5, token probability 0.3); 97% of training clips kept |
|
| 217 |
+
|
| 218 |
+
- Architecture and recipe from tiny-voca: multi-resolution spectral losses for
|
| 219 |
+
the first 8,000 steps, then adversarial (GAN) training with multi-period and
|
| 220 |
+
multi-resolution discriminators.
|
| 221 |
+
- All 60,000 steps ran on one Kaggle Tesla T4 across the two sessions above.
|
| 222 |
+
|
| 223 |
+
## Evaluation
|
| 224 |
+
|
| 225 |
+
These are internal validation numbers on held-out Rasa clips. No listening test
|
| 226 |
+
with a panel of Bengali speakers has been run yet.
|
| 227 |
+
|
| 228 |
+
| Metric | Value |
|
| 229 |
+
|---|---:|
|
| 230 |
+
| Mel loss, teacher-forced (lower is better) | 0.70 |
|
| 231 |
+
| Mel loss, predicted durations | 0.72 |
|
| 232 |
+
| Pitch error (semitones) | 2.07 |
|
| 233 |
+
| Voicing accuracy | 0.93 |
|
| 234 |
+
| Pause accuracy | 0.90 |
|
| 235 |
+
|
| 236 |
+
## Performance
|
| 237 |
+
|
| 238 |
+
This is the fun part. Measured with the INT8 model on CPU using 2 ONNX Runtime
|
| 239 |
+
threads:
|
| 240 |
+
|
| 241 |
+
| | |
|
| 242 |
+
|---|---:|
|
| 243 |
+
| Inference (2 threads) | 103 ms |
|
| 244 |
+
| Generated audio | 4.75 s |
|
| 245 |
+
| Real-time factor | 45.9× |
|
| 246 |
+
| Headroom over playback | ~4.6 s |
|
| 247 |
+
|
| 248 |
+
The test sentence is the 66-token line "গতকাল আমি খুব ব্যস্ত ছিলাম, তাই সন্ধ্যায়
|
| 249 |
+
তোমাকে ফোন করতে পারিনি।". The 103 ms covers the ONNX graph only; phonemization
|
| 250 |
+
with espeak-ng adds about 70 ms on a desktop CPU, and writing the WAV is
|
| 251 |
+
negligible. Speed depends on the CPU and thread count.
|
| 252 |
+
|
| 253 |
+
## Intended use
|
| 254 |
+
|
| 255 |
+
Research and personal projects. Not for impersonating any real person.
|
| 256 |
+
|
| 257 |
+
## Limitations
|
| 258 |
+
|
| 259 |
+
- Bengali with limited code-mixed English; two fixed voices, no voice cloning.
|
| 260 |
+
- Code-mixed English is handled word by word through a small lexicon (213
|
| 261 |
+
entries) plus fallback rules. Foreign names, unusual spellings and words
|
| 262 |
+
outside the lexicon are often mispronounced.
|
| 263 |
+
- Numbers and abbreviations depend on espeak-ng's Bengali frontend.
|
| 264 |
+
- The same text is always read the same way. There is no sampling of prosody.
|
| 265 |
+
- No frame-level streaming; `inference.py` streams sentence by sentence.
|
| 266 |
+
- The INT8 model is smaller and faster, but its output differs slightly from
|
| 267 |
+
the FP32 reference.
|
| 268 |
+
|
| 269 |
+
## License
|
| 270 |
+
|
| 271 |
+
The weights and code are released under Apache-2.0. tiny-swara is built on the
|
| 272 |
+
tiny-voca architecture by Muhammed Nazeem; see
|
| 273 |
+
[n4ze3m/tiny-voca](https://huggingface.co/n4ze3m/tiny-voca). The phoneme
|
| 274 |
+
inventory and lexicon were produced for this model. The training recordings
|
| 275 |
+
come from AI4Bharat Rasa; follow its terms when redistributing derived audio.
|
| 276 |
+
|
| 277 |
+
## Credits
|
| 278 |
+
|
| 279 |
+
- tiny-voca architecture and training code by n4ze3m (Apache-2.0).
|
| 280 |
+
- Bengali recordings from AI4Bharat Rasa.
|
| 281 |
+
- Aligner: `facebook/wav2vec2-lv-60-espeak-cv-ft`.
|
| 282 |
+
- Phonemizer: [espeak-ng](https://github.com/espeak-ng/espeak-ng).
|
config.json
ADDED
|
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model": {
|
| 3 |
+
"sample_rate": 24000,
|
| 4 |
+
"hop": 256,
|
| 5 |
+
"speakers": [
|
| 6 |
+
"BF",
|
| 7 |
+
"BM"
|
| 8 |
+
],
|
| 9 |
+
"vocab_size": 77,
|
| 10 |
+
"channels": 192,
|
| 11 |
+
"heads": 4,
|
| 12 |
+
"feedforward": 640,
|
| 13 |
+
"kernel": 7,
|
| 14 |
+
"encoder_layers": 4,
|
| 15 |
+
"prosody_layers": 2,
|
| 16 |
+
"acoustic_layers": 5,
|
| 17 |
+
"max_tokens": 512,
|
| 18 |
+
"max_frames": 3000
|
| 19 |
+
},
|
| 20 |
+
"step": 60000,
|
| 21 |
+
"sample_rate": 24000,
|
| 22 |
+
"hop": 256,
|
| 23 |
+
"voices": [
|
| 24 |
+
"BF",
|
| 25 |
+
"BM"
|
| 26 |
+
],
|
| 27 |
+
"frontend": "espeak",
|
| 28 |
+
"frontend_fingerprint": "54cece4f400be1fbb56c30bbeedbcdcf5d432702e6d8c6389f44fbb79dc4c94b",
|
| 29 |
+
"stress": {
|
| 30 |
+
"none": 0,
|
| 31 |
+
"primary": 1,
|
| 32 |
+
"secondary": 2
|
| 33 |
+
},
|
| 34 |
+
"onnx": {
|
| 35 |
+
"file": "onnx/tiny-swara.onnx",
|
| 36 |
+
"inputs": [
|
| 37 |
+
"tokens",
|
| 38 |
+
"stress",
|
| 39 |
+
"voice",
|
| 40 |
+
"speed",
|
| 41 |
+
"pitch_shift",
|
| 42 |
+
"pitch_range"
|
| 43 |
+
],
|
| 44 |
+
"outputs": [
|
| 45 |
+
"audio",
|
| 46 |
+
"durations"
|
| 47 |
+
]
|
| 48 |
+
},
|
| 49 |
+
"vocab": {
|
| 50 |
+
"<pad>": 0,
|
| 51 |
+
"<bos>": 1,
|
| 52 |
+
"<eos>": 2,
|
| 53 |
+
"<sp>": 3,
|
| 54 |
+
"<unk>": 4,
|
| 55 |
+
",": 5,
|
| 56 |
+
".": 6,
|
| 57 |
+
"?": 7,
|
| 58 |
+
"!": 8,
|
| 59 |
+
";": 9,
|
| 60 |
+
":": 10,
|
| 61 |
+
"\"": 11,
|
| 62 |
+
"'": 12,
|
| 63 |
+
"(": 13,
|
| 64 |
+
")": 14,
|
| 65 |
+
"—": 15,
|
| 66 |
+
"…": 16,
|
| 67 |
+
"ɾ": 17,
|
| 68 |
+
"n": 18,
|
| 69 |
+
"ʃ": 19,
|
| 70 |
+
"k": 20,
|
| 71 |
+
"t": 21,
|
| 72 |
+
"b": 22,
|
| 73 |
+
"m": 23,
|
| 74 |
+
"l": 24,
|
| 75 |
+
"p": 25,
|
| 76 |
+
"d": 26,
|
| 77 |
+
"h": 27,
|
| 78 |
+
"ʈ": 28,
|
| 79 |
+
"ɟ": 29,
|
| 80 |
+
"ɡ": 30,
|
| 81 |
+
"kʰ": 31,
|
| 82 |
+
"j": 32,
|
| 83 |
+
"tʃʰ": 33,
|
| 84 |
+
"tʃ": 34,
|
| 85 |
+
"ŋ": 35,
|
| 86 |
+
"dʒ": 36,
|
| 87 |
+
"bʰ": 37,
|
| 88 |
+
"tʰ": 38,
|
| 89 |
+
"dʰ": 39,
|
| 90 |
+
"r.": 40,
|
| 91 |
+
"ɖ": 41,
|
| 92 |
+
"s": 42,
|
| 93 |
+
"f": 43,
|
| 94 |
+
"r": 44,
|
| 95 |
+
"ʈʰ": 45,
|
| 96 |
+
"ɡʰ": 46,
|
| 97 |
+
"w": 47,
|
| 98 |
+
"ɟʰ": 48,
|
| 99 |
+
"dʰː": 49,
|
| 100 |
+
"ɖʰ": 50,
|
| 101 |
+
"tː": 51,
|
| 102 |
+
"ɟː": 52,
|
| 103 |
+
"dʒː": 53,
|
| 104 |
+
"kʰː": 54,
|
| 105 |
+
"tʰː": 55,
|
| 106 |
+
"ɡː": 56,
|
| 107 |
+
"cʰ": 57,
|
| 108 |
+
"bː": 58,
|
| 109 |
+
"dː": 59,
|
| 110 |
+
"c": 60,
|
| 111 |
+
"ɔ": 61,
|
| 112 |
+
"a": 62,
|
| 113 |
+
"e": 63,
|
| 114 |
+
"i": 64,
|
| 115 |
+
"o": 65,
|
| 116 |
+
"u": 66,
|
| 117 |
+
"æ": 67,
|
| 118 |
+
"oː": 68,
|
| 119 |
+
"ã": 69,
|
| 120 |
+
"aː": 70,
|
| 121 |
+
"õ": 71,
|
| 122 |
+
"ũ": 72,
|
| 123 |
+
"ɔ̃": 73,
|
| 124 |
+
"ə": 74,
|
| 125 |
+
"ɔː": 75,
|
| 126 |
+
"iː": 76
|
| 127 |
+
},
|
| 128 |
+
"speakers": [
|
| 129 |
+
"BF",
|
| 130 |
+
"BM"
|
| 131 |
+
]
|
| 132 |
+
}
|
inference.py
ADDED
|
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
tiny-swara ONNX inference.
|
| 3 |
+
|
| 4 |
+
Expected repository layout:
|
| 5 |
+
tiny-swara/
|
| 6 |
+
inference.py
|
| 7 |
+
config.json
|
| 8 |
+
inventory.json
|
| 9 |
+
lexicon.json
|
| 10 |
+
tiny_voca/
|
| 11 |
+
__init__.py
|
| 12 |
+
text.py # patched Bengali tiny-voca frontend
|
| 13 |
+
onnx/
|
| 14 |
+
tiny-swara-int8.onnx
|
| 15 |
+
tiny-swara.onnx # optional FP32 model
|
| 16 |
+
|
| 17 |
+
System dependency: espeak-ng
|
| 18 |
+
Python dependencies: numpy, onnxruntime
|
| 19 |
+
|
| 20 |
+
The frontend module must be the Bengali-patched tiny_voca.text from the
|
| 21 |
+
training/export environment. The ONNX graph itself accepts phoneme IDs,
|
| 22 |
+
not raw text.
|
| 23 |
+
"""
|
| 24 |
+
|
| 25 |
+
from __future__ import annotations
|
| 26 |
+
|
| 27 |
+
import argparse
|
| 28 |
+
import json
|
| 29 |
+
import os
|
| 30 |
+
import re
|
| 31 |
+
import wave
|
| 32 |
+
from pathlib import Path
|
| 33 |
+
from typing import Iterator
|
| 34 |
+
|
| 35 |
+
import numpy as np
|
| 36 |
+
import onnxruntime as ort
|
| 37 |
+
|
| 38 |
+
ROOT = Path(__file__).resolve().parent
|
| 39 |
+
|
| 40 |
+
# Set these BEFORE importing tiny_voca.text because it loads the inventory
|
| 41 |
+
# and lexicon when the module is imported.
|
| 42 |
+
os.environ["TINY_VOCA_INVENTORY"] = str(ROOT / "inventory.json")
|
| 43 |
+
os.environ["TINY_VOCA_LEXICON"] = str(ROOT / "lexicon.json")
|
| 44 |
+
os.environ.setdefault("TINY_VOCA_FRONTEND", "espeak")
|
| 45 |
+
|
| 46 |
+
from tiny_voca import text as frontend # noqa: E402
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
def load_config() -> dict:
|
| 50 |
+
path = ROOT / "config.json"
|
| 51 |
+
if not path.exists():
|
| 52 |
+
raise FileNotFoundError(f"Missing model config: {path}")
|
| 53 |
+
return json.loads(path.read_text(encoding="utf-8"))
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
CONFIG = load_config()
|
| 57 |
+
SPEAKERS = CONFIG.get("speakers", ["BF", "BM"])
|
| 58 |
+
SAMPLE_RATE = int(CONFIG.get("sample_rate", 24000))
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
def resolve_model(model: str | Path | None = None) -> Path:
|
| 62 |
+
if model:
|
| 63 |
+
path = Path(model)
|
| 64 |
+
if not path.is_absolute():
|
| 65 |
+
path = ROOT / path
|
| 66 |
+
if path.is_file():
|
| 67 |
+
return path
|
| 68 |
+
raise FileNotFoundError(f"Model file not found: {path}")
|
| 69 |
+
|
| 70 |
+
candidates = [
|
| 71 |
+
ROOT / "onnx" / "tiny-swara-int8.onnx",
|
| 72 |
+
ROOT / "tiny-swara-int8.onnx",
|
| 73 |
+
ROOT / "onnx" / "tiny-swara.onnx",
|
| 74 |
+
ROOT / "tiny-swara.onnx",
|
| 75 |
+
ROOT / "tiny-bn-int8.onnx",
|
| 76 |
+
ROOT / "tiny-bn.onnx",
|
| 77 |
+
]
|
| 78 |
+
for path in candidates:
|
| 79 |
+
if path.is_file():
|
| 80 |
+
return path
|
| 81 |
+
raise FileNotFoundError(
|
| 82 |
+
"Could not find an ONNX model. Put tiny-swara-int8.onnx in onnx/ "
|
| 83 |
+
"or pass --model PATH."
|
| 84 |
+
)
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
def split_sentences(text: str) -> list[str]:
|
| 88 |
+
"""Split at sentence endings while retaining punctuation."""
|
| 89 |
+
text = re.sub(r"\s+", " ", text).strip()
|
| 90 |
+
if not text:
|
| 91 |
+
return []
|
| 92 |
+
|
| 93 |
+
parts = re.split(r"(?<=[.!?।…])\s+", text)
|
| 94 |
+
result = []
|
| 95 |
+
for part in parts:
|
| 96 |
+
part = part.strip()
|
| 97 |
+
if not part:
|
| 98 |
+
continue
|
| 99 |
+
if not re.search(r"[.!?।…][\"'’”)\]]*$", part):
|
| 100 |
+
part += "."
|
| 101 |
+
result.append(part)
|
| 102 |
+
return result
|
| 103 |
+
|
| 104 |
+
|
| 105 |
+
class TinySwara:
|
| 106 |
+
def __init__(
|
| 107 |
+
self,
|
| 108 |
+
model: str | Path | None = None,
|
| 109 |
+
voice: str = "BF",
|
| 110 |
+
speed: float = 1.0,
|
| 111 |
+
pitch_shift: float = 0.0,
|
| 112 |
+
pitch_range: float = 1.0,
|
| 113 |
+
providers: list[str] | None = None,
|
| 114 |
+
):
|
| 115 |
+
if voice not in SPEAKERS:
|
| 116 |
+
raise ValueError(
|
| 117 |
+
f"Unknown voice {voice!r}. Available voices: {', '.join(SPEAKERS)}"
|
| 118 |
+
)
|
| 119 |
+
|
| 120 |
+
self.voice = voice
|
| 121 |
+
self.voice_id = SPEAKERS.index(voice)
|
| 122 |
+
self.speed = float(speed)
|
| 123 |
+
self.pitch_shift = float(pitch_shift)
|
| 124 |
+
self.pitch_range = float(pitch_range)
|
| 125 |
+
self.model_path = resolve_model(model)
|
| 126 |
+
|
| 127 |
+
self.session = ort.InferenceSession(
|
| 128 |
+
str(self.model_path),
|
| 129 |
+
providers=providers or ["CPUExecutionProvider"],
|
| 130 |
+
)
|
| 131 |
+
|
| 132 |
+
required_inputs = {
|
| 133 |
+
"tokens", "stress", "voice", "speed", "pitch_shift", "pitch_range"
|
| 134 |
+
}
|
| 135 |
+
actual_inputs = {item.name for item in self.session.get_inputs()}
|
| 136 |
+
missing = required_inputs - actual_inputs
|
| 137 |
+
if missing:
|
| 138 |
+
raise RuntimeError(
|
| 139 |
+
f"ONNX model is missing expected inputs: {sorted(missing)}. "
|
| 140 |
+
f"Found: {sorted(actual_inputs)}"
|
| 141 |
+
)
|
| 142 |
+
|
| 143 |
+
def synthesize_chunk(self, text: str) -> np.ndarray:
|
| 144 |
+
"""Generate one sentence/utterance and return mono float32 audio."""
|
| 145 |
+
phones = frontend.phonemize(text)
|
| 146 |
+
|
| 147 |
+
if phones.unknown:
|
| 148 |
+
raise ValueError(
|
| 149 |
+
f"Unmapped phonemes in {text!r}: {phones.unknown}. "
|
| 150 |
+
"Check inventory.json and lexicon.json."
|
| 151 |
+
)
|
| 152 |
+
|
| 153 |
+
inputs = {
|
| 154 |
+
"tokens": np.asarray([phones.ids], dtype=np.int64),
|
| 155 |
+
"stress": np.asarray([phones.stress], dtype=np.int64),
|
| 156 |
+
"voice": np.asarray([self.voice_id], dtype=np.int64),
|
| 157 |
+
"speed": np.asarray([self.speed], dtype=np.float32),
|
| 158 |
+
"pitch_shift": np.asarray([self.pitch_shift], dtype=np.float32),
|
| 159 |
+
"pitch_range": np.asarray([self.pitch_range], dtype=np.float32),
|
| 160 |
+
}
|
| 161 |
+
|
| 162 |
+
audio, _durations = self.session.run(["audio", "durations"], inputs)
|
| 163 |
+
wave = np.asarray(audio[0], dtype=np.float32).reshape(-1)
|
| 164 |
+
|
| 165 |
+
if wave.size == 0 or not np.isfinite(wave).all():
|
| 166 |
+
raise RuntimeError("ONNX model returned empty or non-finite audio.")
|
| 167 |
+
|
| 168 |
+
peak = float(np.max(np.abs(wave)))
|
| 169 |
+
if peak > 0:
|
| 170 |
+
wave = wave * (0.9 / peak)
|
| 171 |
+
|
| 172 |
+
return wave
|
| 173 |
+
|
| 174 |
+
def stream(self, text: str) -> Iterator[np.ndarray]:
|
| 175 |
+
"""
|
| 176 |
+
Yield one generated sentence at a time.
|
| 177 |
+
This is sentence-level streaming: each sentence is generated fully
|
| 178 |
+
before it is yielded; it is not frame-by-frame neural streaming.
|
| 179 |
+
"""
|
| 180 |
+
sentences = split_sentences(text)
|
| 181 |
+
if not sentences:
|
| 182 |
+
raise ValueError("Text is empty.")
|
| 183 |
+
|
| 184 |
+
for sentence in sentences:
|
| 185 |
+
yield self.synthesize_chunk(sentence)
|
| 186 |
+
|
| 187 |
+
def synthesize(self, text: str) -> np.ndarray:
|
| 188 |
+
"""Generate a complete utterance by joining sentence audio chunks."""
|
| 189 |
+
chunks = list(self.stream(text))
|
| 190 |
+
return np.concatenate(chunks) if len(chunks) > 1 else chunks[0]
|
| 191 |
+
|
| 192 |
+
def save(self, text: str, output_path: str | Path) -> Path:
|
| 193 |
+
output_path = Path(output_path)
|
| 194 |
+
if not output_path.is_absolute():
|
| 195 |
+
output_path = Path.cwd() / output_path
|
| 196 |
+
output_path.parent.mkdir(parents=True, exist_ok=True)
|
| 197 |
+
audio = self.synthesize(text)
|
| 198 |
+
pcm = np.clip(audio * 32767.0, -32768, 32767).astype("<i2")
|
| 199 |
+
with wave.open(str(output_path), "wb") as f:
|
| 200 |
+
f.setnchannels(1)
|
| 201 |
+
f.setsampwidth(2)
|
| 202 |
+
f.setframerate(SAMPLE_RATE)
|
| 203 |
+
f.writeframes(pcm.tobytes())
|
| 204 |
+
return output_path
|
| 205 |
+
|
| 206 |
+
|
| 207 |
+
def main() -> None:
|
| 208 |
+
parser = argparse.ArgumentParser(description="tiny-swara Bengali ONNX TTS")
|
| 209 |
+
parser.add_argument("--text", help="Text to synthesize")
|
| 210 |
+
parser.add_argument("--text-file", help="UTF-8 text file to synthesize")
|
| 211 |
+
parser.add_argument("--output", default="tiny-swara.wav")
|
| 212 |
+
parser.add_argument("--model", help="Optional ONNX model path")
|
| 213 |
+
parser.add_argument("--voice", default="BF", choices=SPEAKERS)
|
| 214 |
+
parser.add_argument("--speed", type=float, default=1.0)
|
| 215 |
+
parser.add_argument("--pitch-shift", type=float, default=0.0)
|
| 216 |
+
parser.add_argument("--pitch-range", type=float, default=1.0)
|
| 217 |
+
args = parser.parse_args()
|
| 218 |
+
|
| 219 |
+
if bool(args.text) == bool(args.text_file):
|
| 220 |
+
parser.error("Provide exactly one of --text or --text-file.")
|
| 221 |
+
|
| 222 |
+
text = (
|
| 223 |
+
Path(args.text_file).read_text(encoding="utf-8")
|
| 224 |
+
if args.text_file
|
| 225 |
+
else args.text
|
| 226 |
+
)
|
| 227 |
+
|
| 228 |
+
tts = TinySwara(
|
| 229 |
+
model=args.model,
|
| 230 |
+
voice=args.voice,
|
| 231 |
+
speed=args.speed,
|
| 232 |
+
pitch_shift=args.pitch_shift,
|
| 233 |
+
pitch_range=args.pitch_range,
|
| 234 |
+
)
|
| 235 |
+
saved = tts.save(text, args.output)
|
| 236 |
+
print(f"Saved: {saved} ({SAMPLE_RATE} Hz, voice={args.voice})")
|
| 237 |
+
print(f"Model: {tts.model_path}")
|
| 238 |
+
|
| 239 |
+
|
| 240 |
+
if __name__ == "__main__":
|
| 241 |
+
main()
|
inventory.json
ADDED
|
@@ -0,0 +1,211 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"voice": "bn",
|
| 3 |
+
"consonants": [
|
| 4 |
+
"ɾ",
|
| 5 |
+
"n",
|
| 6 |
+
"ʃ",
|
| 7 |
+
"k",
|
| 8 |
+
"t",
|
| 9 |
+
"b",
|
| 10 |
+
"m",
|
| 11 |
+
"l",
|
| 12 |
+
"p",
|
| 13 |
+
"d",
|
| 14 |
+
"h",
|
| 15 |
+
"ʈ",
|
| 16 |
+
"ɟ",
|
| 17 |
+
"ɡ",
|
| 18 |
+
"kʰ",
|
| 19 |
+
"j",
|
| 20 |
+
"tʃʰ",
|
| 21 |
+
"tʃ",
|
| 22 |
+
"ŋ",
|
| 23 |
+
"dʒ",
|
| 24 |
+
"bʰ",
|
| 25 |
+
"tʰ",
|
| 26 |
+
"dʰ",
|
| 27 |
+
"r.",
|
| 28 |
+
"ɖ",
|
| 29 |
+
"s",
|
| 30 |
+
"f",
|
| 31 |
+
"r",
|
| 32 |
+
"ʈʰ",
|
| 33 |
+
"ɡʰ",
|
| 34 |
+
"w",
|
| 35 |
+
"ɟʰ",
|
| 36 |
+
"dʰː",
|
| 37 |
+
"ɖʰ",
|
| 38 |
+
"tː",
|
| 39 |
+
"ɟː",
|
| 40 |
+
"dʒː",
|
| 41 |
+
"kʰː",
|
| 42 |
+
"tʰː",
|
| 43 |
+
"ɡː",
|
| 44 |
+
"cʰ",
|
| 45 |
+
"bː",
|
| 46 |
+
"dː",
|
| 47 |
+
"c"
|
| 48 |
+
],
|
| 49 |
+
"vowels": [
|
| 50 |
+
"ɔ",
|
| 51 |
+
"a",
|
| 52 |
+
"e",
|
| 53 |
+
"i",
|
| 54 |
+
"o",
|
| 55 |
+
"u",
|
| 56 |
+
"æ",
|
| 57 |
+
"oː",
|
| 58 |
+
"ã",
|
| 59 |
+
"aː",
|
| 60 |
+
"õ",
|
| 61 |
+
"ũ",
|
| 62 |
+
"ɔ̃",
|
| 63 |
+
"ə",
|
| 64 |
+
"ɔː",
|
| 65 |
+
"iː"
|
| 66 |
+
],
|
| 67 |
+
"voiceless": [
|
| 68 |
+
"ʃ",
|
| 69 |
+
"k",
|
| 70 |
+
"t",
|
| 71 |
+
"p",
|
| 72 |
+
"h",
|
| 73 |
+
"ʈ",
|
| 74 |
+
"kʰ",
|
| 75 |
+
"tʃʰ",
|
| 76 |
+
"tʃ",
|
| 77 |
+
"tʰ",
|
| 78 |
+
"s",
|
| 79 |
+
"f",
|
| 80 |
+
"ʈʰ",
|
| 81 |
+
"tː",
|
| 82 |
+
"kʰː",
|
| 83 |
+
"tʰː",
|
| 84 |
+
"cʰ",
|
| 85 |
+
"c"
|
| 86 |
+
],
|
| 87 |
+
"fallback": {
|
| 88 |
+
"ʈʈ": [
|
| 89 |
+
"ʈ"
|
| 90 |
+
],
|
| 91 |
+
"kː": [
|
| 92 |
+
"k"
|
| 93 |
+
],
|
| 94 |
+
"ĩ": [
|
| 95 |
+
"i"
|
| 96 |
+
],
|
| 97 |
+
"ẽ": [
|
| 98 |
+
"e"
|
| 99 |
+
],
|
| 100 |
+
"pː": [
|
| 101 |
+
"p"
|
| 102 |
+
],
|
| 103 |
+
"ɡʰː": [
|
| 104 |
+
"ɡː"
|
| 105 |
+
],
|
| 106 |
+
"p̃": [
|
| 107 |
+
"p"
|
| 108 |
+
],
|
| 109 |
+
"l̩": [
|
| 110 |
+
"l"
|
| 111 |
+
],
|
| 112 |
+
"ʈʰʈʰ": [
|
| 113 |
+
"ʈ"
|
| 114 |
+
],
|
| 115 |
+
"ɖɖ": [
|
| 116 |
+
"ɖ"
|
| 117 |
+
],
|
| 118 |
+
"æ": [
|
| 119 |
+
"a"
|
| 120 |
+
],
|
| 121 |
+
"ɑ": [
|
| 122 |
+
"a"
|
| 123 |
+
],
|
| 124 |
+
"ɛ": [
|
| 125 |
+
"e"
|
| 126 |
+
],
|
| 127 |
+
"ɪ": [
|
| 128 |
+
"i"
|
| 129 |
+
],
|
| 130 |
+
"ᵻ": [
|
| 131 |
+
"i"
|
| 132 |
+
],
|
| 133 |
+
"ʊ": [
|
| 134 |
+
"u"
|
| 135 |
+
],
|
| 136 |
+
"ʌ": [
|
| 137 |
+
"ɔ"
|
| 138 |
+
],
|
| 139 |
+
"ə": [
|
| 140 |
+
"ɔ"
|
| 141 |
+
],
|
| 142 |
+
"ɐ": [
|
| 143 |
+
"ɔ"
|
| 144 |
+
],
|
| 145 |
+
"ɜ": [
|
| 146 |
+
"ɔ"
|
| 147 |
+
],
|
| 148 |
+
"ɚ": [
|
| 149 |
+
"ɔ",
|
| 150 |
+
"ɾ"
|
| 151 |
+
],
|
| 152 |
+
"ɝ": [
|
| 153 |
+
"ɔ",
|
| 154 |
+
"ɾ"
|
| 155 |
+
],
|
| 156 |
+
"ɔː": [
|
| 157 |
+
"ɔ"
|
| 158 |
+
],
|
| 159 |
+
"ɔːɹ": [
|
| 160 |
+
"ɔ",
|
| 161 |
+
"ɾ"
|
| 162 |
+
],
|
| 163 |
+
"ɹ": [
|
| 164 |
+
"ɾ"
|
| 165 |
+
],
|
| 166 |
+
"θ": [
|
| 167 |
+
"tʰ"
|
| 168 |
+
],
|
| 169 |
+
"ð": [
|
| 170 |
+
"d"
|
| 171 |
+
],
|
| 172 |
+
"v": [
|
| 173 |
+
"b"
|
| 174 |
+
],
|
| 175 |
+
"f": [
|
| 176 |
+
"p"
|
| 177 |
+
],
|
| 178 |
+
"z": [
|
| 179 |
+
"dʒ"
|
| 180 |
+
],
|
| 181 |
+
"ʒ": [
|
| 182 |
+
"ʃ"
|
| 183 |
+
],
|
| 184 |
+
"w": [
|
| 185 |
+
"o"
|
| 186 |
+
],
|
| 187 |
+
"aɪ": [
|
| 188 |
+
"a",
|
| 189 |
+
"i"
|
| 190 |
+
],
|
| 191 |
+
"aʊ": [
|
| 192 |
+
"a",
|
| 193 |
+
"u"
|
| 194 |
+
],
|
| 195 |
+
"eɪ": [
|
| 196 |
+
"e",
|
| 197 |
+
"i"
|
| 198 |
+
],
|
| 199 |
+
"oʊ": [
|
| 200 |
+
"o",
|
| 201 |
+
"u"
|
| 202 |
+
],
|
| 203 |
+
"ɔɪ": [
|
| 204 |
+
"ɔ",
|
| 205 |
+
"i"
|
| 206 |
+
]
|
| 207 |
+
},
|
| 208 |
+
"aligner_labels": {
|
| 209 |
+
"tʰː": "tː"
|
| 210 |
+
}
|
| 211 |
+
}
|
lexicon.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"order": "অর্ডার", "orders": "অর্ডারস", "refund": "রিফান্ড", "refunded": "রিফান্ডেড", "status": "স্ট্যাটাস", "delivery": "ডেলিভারি", "account": "অ্যাকাউন্ট", "phone": "ফোন", "mobile": "মোবাইল", "number": "নাম্বার", "password": "পাসওয়ার্ড", "login": "লগইন", "email": "ইমেইল", "payment": "পেমেন্ট", "cancel": "ক্যানসেল", "cancelled": "ক্যানসেলড", "confirm": "কনফার্ম", "booking": "বুকিং", "ticket": "টিকিট", "call": "কল", "message": "মেসেজ", "app": "অ্যাপ", "website": "ওয়েবসাইট", "online": "অনলাইন", "update": "আপডেট", "download": "ডাউনলোড", "internet": "ইন্টারনেট", "okay": "ওকে", "ok": "ওকে", "sorry": "সরি", "thanks": "থ্যাঙ্কস", "hello": "হ্যালো", "help": "হেল্প", "support": "সাপোর্ট", "service": "সার্ভিস", "customer": "কাস্টমার", "address": "অ্যাড্রেস", "card": "কার্ড", "bank": "ব্যাংক", "balance": "ব্যালেন্স", "recharge": "রিচার্জ", "data": "ডাটা", "offer": "অফার", "discount": "ডিসকাউন্ট", "id": "আইডি", "otp": "ও টি পি", "version": "ভার্সন", "tracking": "ট্র্যাকিং", "track": "ট্র্যাক", "orderid": "অর্ডার আইডি", "search": "সার্চ", "find": "ফাইন্ড", "check": "চেক", "show": "শো", "open": "ওপেন", "close": "ক্লোজ", "start": "স্টার্ট", "stop": "স্টপ", "pause": "পজ", "resume": "রিজিউম", "skip": "স্কিপ", "next": "নেক্সট", "previous": "প্রিভিয়াস", "back": "ব্যাক", "save": "সেভ", "delete": "ডিলিট", "remove": "রিমুভ", "edit": "এডিট", "change": "চেঞ্জ", "reset": "রিসেট", "retry": "রিট্রাই", "send": "সেন্ড", "share": "শেয়ার", "copy": "কপি", "paste": "পেস্ট", "upload": "আপলোড", "select": "সিলেক্ট", "submit": "সাবমিট", "apply": "অ্যাপ্লাই", "enable": "এনেবল", "disable": "ডিসেবল", "turn": "টার্ন", "switch": "সুইচ", "time": "টাইম", "date": "ডেট", "today": "টুডে", "tomorrow": "টুমরো", "yesterday": "ইয়েস্টারডে", "week": "উইক", "month": "মান্থ", "year": "ইয়ার", "morning": "মর্নিং", "evening": "ইভিনিং", "night": "নাইট", "minute": "মিনিট", "minutes": "মিনিটস", "hour": "আওয়ার", "hours": "আওয়ারস", "alarm": "অ্যালার্ম", "reminder": "রিমাইন্ডার", "schedule": "শিডিউল", "meeting": "মিটিং", "appointment": "অ্যাপয়েন্টমেন্ট", "deadline": "ডেডলাইন", "late": "লেট", "early": "আর্লি", "screen": "স্ক্রিন", "battery": "ব্যাটারি", "charge": "চার্জ", "charger": "চার্জার", "wifi": "ওয়াইফাই", "network": "নেটওয়ার্ক", "signal": "সিগন্যাল", "bluetooth": "ব্লুটুথ", "volume": "ভলিউম", "sound": "সাউন্ড", "mute": "মিউট", "notification": "নোটিফিকেশন", "notifications": "নোটিফিকেশনস", "setting": "সেটিং", "settings": "সেটিংস", "link": "লিংক", "url": "ইউ আর এল", "file": "ফাইল", "files": "ফাইলস", "folder": "ফোল্ডার", "photo": "ফটো", "photos": "ফটোজ", "video": "ভিডিও", "audio": "অডিও", "music": "মিউজিক", "camera": "ক্যামেরা", "mic": "মাইক", "speaker": "স্পিকার", "browser": "ব্রাউজার", "tab": "ট্যাব", "page": "পেজ", "login_id": "লগইন আইডি", "username": "ইউজারনেম", "profile": "প্রোফাইল", "logout": "লগআউট", "signup": "সাইনআপ", "pin": "পিন", "code": "কোড", "qr": "কিউ আর", "scan": "স্ক্যান", "price": "প্রাইস", "cost": "কস্ট", "amount": "অ্যামাউন্ট", "total": "টোটাল", "bill": "বিল", "invoice": "ইনভয়েস", "receipt": "রিসিট", "upi": "ইউ পি আই", "wallet": "ওয়ালেট", "cash": "ক্যাশ", "pay": "পে", "paid": "পেইড", "due": "ডিউ", "pending": "পেন্ডিং", "completed": "কমপ্লিটেড", "failed": "ফেইল্ড", "success": "সাকসেস", "error": "এরর", "issue": "ইস্যু", "problem": "প্রবলেম", "fix": "ফিক্স", "solution": "সলিউশন", "plan": "প্ল্যান", "limit": "লিমিট", "location": "লোকেশন", "map": "ম্যাপ", "route": "রুট", "weather": "ওয়েদার", "temperature": "টেম্পারেচার", "news": "নিউজ", "notes": "নোটস", "note": "নোট", "list": "লিস্ট", "item": "আইটেম", "items": "আইটেমস", "cart": "কার্ট", "checkout": "চেকআউট", "coupon": "কুপন", "voucher": "ভাউচার", "return": "রিটার্ন", "exchange": "এক্সচেঞ্জ", "warranty": "ওয়ারেন্টি", "complaint": "কমপ্লেইন্ট", "please": "প্লিজ", "welcome": "ওয়েলকাম", "bye": "বাই", "goodbye": "গুডবাই", "good": "গুড", "nice": "নাইস", "great": "গ্রেট", "fine": "ফাইন", "sure": "শিওর", "yes": "ইয়েস", "no": "নো", "maybe": "মেবি", "wait": "ওয়েট", "hold": "হোল্ড", "done": "ডান", "ready": "রেডি", "clear": "ক্লিয়ার", "exact": "এক্স্যাক্ট", "extra": "এক্সট্রা", "free": "ফ্রি", "fast": "ফাস্ট", "slow": "স্লো", "important": "ইম্পর্ট্যান্ট", "urgent": "আর্জেন্ট"}
|
onnx/tiny-swara-int8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3080233715cf22ebf519cfc1f81a8ebe4c937c0cdce0285b2cf51998c64eabb
|
| 3 |
+
size 8643037
|
tiny-bn.onnx → onnx/tiny-swara.onnx
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21387142
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cef829cff4b6cb38554e32d8f96b9b51f96a4c0e9cb2e406b53ac79d5923d630
|
| 3 |
size 21387142
|
requirements.txt
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
numpy>=1.24
|
| 2 |
+
onnxruntime>=1.16
|
samples/bf-1.mp3
ADDED
|
Binary file (11 kB). View file
|
|
|
samples/bf-2.mp3
ADDED
|
Binary file (38.3 kB). View file
|
|
|
samples/bf-3.mp3
ADDED
|
Binary file (21.5 kB). View file
|
|
|
samples/bf-4.mp3
ADDED
|
Binary file (28.5 kB). View file
|
|
|
samples/bf-5.mp3
ADDED
|
Binary file (14.6 kB). View file
|
|
|
samples/bm-1.mp3
ADDED
|
Binary file (10.2 kB). View file
|
|
|
samples/bm-2.mp3
ADDED
|
Binary file (34.2 kB). View file
|
|
|
samples/bm-3.mp3
ADDED
|
Binary file (17.7 kB). View file
|
|
|
samples/bm-4.mp3
ADDED
|
Binary file (25.6 kB). View file
|
|
|
samples/bm-5.mp3
ADDED
|
Binary file (13.1 kB). View file
|
|
|
samples/int8-code-mixed.mp3
ADDED
|
Binary file (27.5 kB). View file
|
|
|
samples/int8-female.mp3
ADDED
|
Binary file (26.9 kB). View file
|
|
|
samples/int8-male.mp3
ADDED
|
Binary file (45 kB). View file
|
|
|
tiny_voca/__init__.py
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Bengali front end for tiny-swara (patched from tiny-voca).
|
| 2 |
+
|
| 3 |
+
Only :mod:`tiny_voca.text` is needed for ONNX inference.
|
| 4 |
+
"""
|
tiny_voca/text.py
ADDED
|
@@ -0,0 +1,352 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""English front end: text -> phoneme tokens with a stress feature.
|
| 2 |
+
|
| 3 |
+
The same code runs during annotation, training-set preparation and inference,
|
| 4 |
+
so tokens can never drift between them. Two programs can produce the phonemes:
|
| 5 |
+
|
| 6 |
+
* ``espeak`` (front-end version 3, the default): eSpeak NG, as described below.
|
| 7 |
+
The current checkpoints and annotations were made with it.
|
| 8 |
+
* ``own`` (front-end version 4): the separate ``dizione`` package, a dictionary
|
| 9 |
+
built from CMUdict, a small model for unknown words and rules. No eSpeak, so
|
| 10 |
+
the whole system can be shipped under a permissive licence. Same 76 symbols.
|
| 11 |
+
|
| 12 |
+
Choose with ``set_frontend("own")`` or ``TINY_VOCA_FRONTEND=own``. Everything
|
| 13 |
+
below about tokens holds for both; the rest of this note is the eSpeak path.
|
| 14 |
+
|
| 15 |
+
* eSpeak NG (``en-us``) is the only pronunciation source. It is an external
|
| 16 |
+
rule-based program: no neural G2P and no downloaded weights.
|
| 17 |
+
* A token is one eSpeak phoneme exactly as eSpeak segments it (``--sep``), for
|
| 18 |
+
example ``t``, ``aɪ``, ``ɑːɹ`` or ``n̩``. This is also the label inventory of
|
| 19 |
+
the phoneme recogniser used for offline forced alignment, so one aligned
|
| 20 |
+
label corresponds to exactly one token.
|
| 21 |
+
* Lexical stress is a parallel feature (0 none, 1 primary, 2 secondary), not a
|
| 22 |
+
token, so it never has to be given audio frames.
|
| 23 |
+
* Punctuation, word boundaries and the utterance edges are explicit tokens that
|
| 24 |
+
may last zero frames. They carry pauses when the recording has them.
|
| 25 |
+
|
| 26 |
+
Versions 1 and 2 encoded IPA as UTF-8 bytes and piped text to eSpeak without a
|
| 27 |
+
final newline; eSpeak NG 1.51 then drops the last character of the input, so
|
| 28 |
+
the final phonemes of every clause were wrong. Version 3 terminates the input
|
| 29 |
+
and has a regression test for it.
|
| 30 |
+
"""
|
| 31 |
+
|
| 32 |
+
from dataclasses import dataclass
|
| 33 |
+
import hashlib
|
| 34 |
+
import json
|
| 35 |
+
import os
|
| 36 |
+
import re
|
| 37 |
+
import shutil
|
| 38 |
+
import subprocess
|
| 39 |
+
import unicodedata
|
| 40 |
+
|
| 41 |
+
FRONTEND_VERSION = 3
|
| 42 |
+
ESPEAK_VOICE = "en-us"
|
| 43 |
+
SEPARATOR = "_"
|
| 44 |
+
FRONTENDS = ("espeak", "own")
|
| 45 |
+
FRONTEND_VARIABLE = "TINY_VOCA_FRONTEND"
|
| 46 |
+
_frontend = os.environ.get(FRONTEND_VARIABLE, "espeak")
|
| 47 |
+
if _frontend not in FRONTENDS:
|
| 48 |
+
raise ValueError(f"{FRONTEND_VARIABLE} must be one of {FRONTENDS}, not {_frontend!r}")
|
| 49 |
+
|
| 50 |
+
PAD, BOS, EOS, SP, UNK = "<pad>", "<bos>", "<eos>", "<sp>", "<unk>"
|
| 51 |
+
SPECIALS = (PAD, BOS, EOS, SP, UNK)
|
| 52 |
+
PUNCTUATION = (",", ".", "?", "!", ";", ":", '"', "'", "(", ")", "—", "…")
|
| 53 |
+
CONSONANTS = ("p", "b", "t", "d", "k", "ɡ", "f", "v", "θ", "ð", "s", "z", "ʃ", "ʒ", "h",
|
| 54 |
+
"m", "n", "ŋ", "l", "ɹ", "j", "w", "tʃ", "dʒ", "ɾ", "ʔ")
|
| 55 |
+
VOWELS = ("ə", "ɐ", "ɚ", "ᵻ", "ɪ", "i", "iː", "ɛ", "æ", "ʌ", "ɑː", "ɔ", "ɔː", "ʊ", "uː", "ɜː",
|
| 56 |
+
"eɪ", "aɪ", "ɔɪ", "oʊ", "aʊ", "iə", "oː",
|
| 57 |
+
"ɑːɹ", "ɔːɹ", "oːɹ", "ɪɹ", "ɛɹ", "ʊɹ", "aɪɚ", "aɪə", "əl", "n̩")
|
| 58 |
+
PHONES = CONSONANTS + VOWELS
|
| 59 |
+
# Append-only: changing the order or removing a symbol invalidates checkpoints.
|
| 60 |
+
SYMBOLS = SPECIALS + PUNCTUATION + PHONES
|
| 61 |
+
SYMBOL_TO_ID = {symbol: index for index, symbol in enumerate(SYMBOLS)}
|
| 62 |
+
PHONE_SET = frozenset(PHONES)
|
| 63 |
+
PHONE_IDS = frozenset(SYMBOL_TO_ID[p] for p in PHONES) | {SYMBOL_TO_ID[UNK]}
|
| 64 |
+
VOICELESS = frozenset(("p", "t", "k", "f", "θ", "s", "ʃ", "h", "tʃ", "ʔ"))
|
| 65 |
+
VOWEL_SET = frozenset(VOWELS)
|
| 66 |
+
STRESS_MARKS = {"ˈ": 1, "ˌ": 2}
|
| 67 |
+
|
| 68 |
+
# eSpeak phonemes outside the inventory (foreign words, rare allophones) map to
|
| 69 |
+
# the closest inventory phone(s). Anything else becomes <unk> and is reported.
|
| 70 |
+
FALLBACK = {
|
| 71 |
+
"r": ("ɹ",), "ɻ": ("ɹ",), "ʁ": ("ɹ",), "x": ("k",), "ç": ("h",), "ɬ": ("l",), "ɫ": ("l",), "ɲ": ("n", "j"),
|
| 72 |
+
"ts": ("t", "s"), "dz": ("d", "z"), "β": ("v",), "ɣ": ("ɡ",), "ʎ": ("l", "j"),
|
| 73 |
+
"a": ("æ",), "aː": ("ɑː",), "ɑ": ("ɑː",), "ɒ": ("ɑː",), "ɑ̃": ("ɑː",), "ɔ̃": ("ɔː",), "ɛ̃": ("æ",),
|
| 74 |
+
"e": ("eɪ",), "eː": ("eɪ",), "o": ("oʊ",), "u": ("uː",), "y": ("uː",), "yː": ("uː",),
|
| 75 |
+
"ø": ("ɜː",), "øː": ("ɜː",), "œ": ("ɜː",), "ɜ": ("ɜː",), "ɛː": ("ɛ",), "ɪː": ("ɪ",),
|
| 76 |
+
"əʊ": ("oʊ",), "eə": ("ɛɹ",), "ɪə": ("iə",), "ʊə": ("ʊɹ",), "aʊɚ": ("aʊ", "ɚ"), "l̩": ("əl",), "m̩": ("ə", "m"),
|
| 77 |
+
}
|
| 78 |
+
|
| 79 |
+
# --- bengali-patch ---
|
| 80 |
+
INVENTORY_VARIABLE = "TINY_VOCA_INVENTORY"
|
| 81 |
+
ALIGNER_LABELS = {} # inventory phone -> label of the aligner recogniser (when they differ)
|
| 82 |
+
if os.environ.get(INVENTORY_VARIABLE):
|
| 83 |
+
_inv = json.load(open(os.environ[INVENTORY_VARIABLE], encoding="utf-8"))
|
| 84 |
+
ESPEAK_VOICE = _inv["voice"]
|
| 85 |
+
CONSONANTS = tuple(_inv["consonants"])
|
| 86 |
+
VOWELS = tuple(_inv["vowels"])
|
| 87 |
+
VOICELESS = frozenset(_inv["voiceless"])
|
| 88 |
+
FALLBACK = {k: tuple(v) for k, v in _inv["fallback"].items()}
|
| 89 |
+
ALIGNER_LABELS = dict(_inv.get("aligner_labels", {}))
|
| 90 |
+
PHONES = CONSONANTS + VOWELS
|
| 91 |
+
SYMBOLS = SPECIALS + PUNCTUATION + PHONES
|
| 92 |
+
SYMBOL_TO_ID = {symbol: index for index, symbol in enumerate(SYMBOLS)}
|
| 93 |
+
PHONE_SET = frozenset(PHONES)
|
| 94 |
+
PHONE_IDS = frozenset(SYMBOL_TO_ID[p] for p in PHONES) | {SYMBOL_TO_ID[UNK]}
|
| 95 |
+
VOWEL_SET = frozenset(VOWELS)
|
| 96 |
+
|
| 97 |
+
_QUOTES = str.maketrans({"‘": "'", "’": "'", "‚": "'", "‛": "'", "`": "'", "´": "'",
|
| 98 |
+
"“": '"', "”": '"', "„": '"', "‟": '"', "«": '"', "»": '"',
|
| 99 |
+
"–": "—", "―": "—", "।": ".", "॥": ".", "[": "(", "{": "(", "]": ")", "}": ")"})
|
| 100 |
+
_PUNCTUATION_CHARS = frozenset(PUNCTUATION)
|
| 101 |
+
ABBREVIATIONS = {"mr", "mrs", "ms", "dr", "prof", "st", "jr", "sr", "vs", "etc"}
|
| 102 |
+
_LANGUAGE_TAG = re.compile(r"\((?:_?[a-z0-9]_?){2,3}(?:-(?:_?[a-z0-9]_?)+)*\)")
|
| 103 |
+
|
| 104 |
+
|
| 105 |
+
class NothingToPronounce(ValueError):
|
| 106 |
+
"""The text has no word, number or letter to say: only marks, emoji and the like."""
|
| 107 |
+
|
| 108 |
+
|
| 109 |
+
@dataclass(frozen=True)
|
| 110 |
+
class Phonemized:
|
| 111 |
+
symbols: tuple
|
| 112 |
+
ids: tuple
|
| 113 |
+
stress: tuple
|
| 114 |
+
unknown: tuple # eSpeak phonemes that had no inventory mapping
|
| 115 |
+
|
| 116 |
+
def __len__(self):
|
| 117 |
+
return len(self.ids)
|
| 118 |
+
|
| 119 |
+
|
| 120 |
+
def frontend():
|
| 121 |
+
"""Name of the program that produces the phonemes: ``"espeak"`` or ``"own"``."""
|
| 122 |
+
return _frontend
|
| 123 |
+
|
| 124 |
+
|
| 125 |
+
def set_frontend(name):
|
| 126 |
+
"""Select the phonemizer for this process. Tokens of the two front ends
|
| 127 |
+
must not be mixed: annotations and checkpoints record which one made them."""
|
| 128 |
+
global _frontend
|
| 129 |
+
if name not in FRONTENDS:
|
| 130 |
+
raise ValueError(f"front end must be one of {FRONTENDS}, not {name!r}")
|
| 131 |
+
_frontend = name
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
def _dizione():
|
| 135 |
+
try:
|
| 136 |
+
import dizione
|
| 137 |
+
except ImportError as error:
|
| 138 |
+
raise RuntimeError('the "own" front end needs the dizione package: pip install dizione') from error
|
| 139 |
+
if tuple(dizione.symbols.SYMBOLS) != SYMBOLS:
|
| 140 |
+
raise RuntimeError("dizione's symbol inventory differs from this model's")
|
| 141 |
+
return dizione
|
| 142 |
+
|
| 143 |
+
|
| 144 |
+
def frontend_identity():
|
| 145 |
+
if _frontend == "own":
|
| 146 |
+
phonemizer = _dizione()
|
| 147 |
+
return {"frontend_version": phonemizer.VERSION, "phonemizer": "dizione", "symbols": list(SYMBOLS)}
|
| 148 |
+
return {"frontend_version": FRONTEND_VERSION, "voice": ESPEAK_VOICE, "separator": SEPARATOR,
|
| 149 |
+
"symbols": list(SYMBOLS), "fallback": {key: list(value) for key, value in sorted(FALLBACK.items())}}
|
| 150 |
+
|
| 151 |
+
|
| 152 |
+
def frontend_runtime():
|
| 153 |
+
"""What an annotation run records about the exact program behind its
|
| 154 |
+
tokens: the eSpeak version, or the fingerprint of the phonemizer build."""
|
| 155 |
+
if _frontend == "own":
|
| 156 |
+
return {"phonemizer": _dizione().identity()["fingerprint"]}
|
| 157 |
+
return {"espeak_version": espeak_version()}
|
| 158 |
+
|
| 159 |
+
|
| 160 |
+
def frontend_fingerprint():
|
| 161 |
+
return hashlib.sha256(json.dumps(frontend_identity(), sort_keys=True, ensure_ascii=False).encode()).hexdigest()
|
| 162 |
+
|
| 163 |
+
|
| 164 |
+
def normalize_text(text):
|
| 165 |
+
text = unicodedata.normalize("NFKC", text).translate(_QUOTES)
|
| 166 |
+
text = re.sub(r"\.{3,}", "…", text)
|
| 167 |
+
text = re.sub(r"-{2,}|\s-\s", "—", text)
|
| 168 |
+
return re.sub(r"\s+", " ", text).strip()
|
| 169 |
+
|
| 170 |
+
|
| 171 |
+
def chunks(text):
|
| 172 |
+
"""Yield ``(is_punctuation, piece)``. Decimals, clock times, digit groups,
|
| 173 |
+
contractions, title abbreviations and initialisms stay inside the text piece
|
| 174 |
+
for eSpeak; every other punctuation mark becomes its own token."""
|
| 175 |
+
start = 0
|
| 176 |
+
for i, char in enumerate(text):
|
| 177 |
+
if char not in _PUNCTUATION_CHARS:
|
| 178 |
+
continue
|
| 179 |
+
previous = text[i-1] if i else ""
|
| 180 |
+
following = text[i+1] if i+1 < len(text) else ""
|
| 181 |
+
if char == "'" and previous.isalnum() and following.isalnum():
|
| 182 |
+
continue
|
| 183 |
+
if char in ".,:" and previous.isdigit() and following.isdigit():
|
| 184 |
+
continue
|
| 185 |
+
if char == ".":
|
| 186 |
+
word = re.search(r"([A-Za-z]+)$", text[:i])
|
| 187 |
+
if word and word[1].lower() in ABBREVIATIONS:
|
| 188 |
+
continue
|
| 189 |
+
if previous.isalpha() and following.isalpha():
|
| 190 |
+
continue
|
| 191 |
+
if text[start:i].strip():
|
| 192 |
+
yield False, text[start:i].strip()
|
| 193 |
+
yield True, char
|
| 194 |
+
start = i+1
|
| 195 |
+
if text[start:].strip():
|
| 196 |
+
yield False, text[start:].strip()
|
| 197 |
+
|
| 198 |
+
|
| 199 |
+
def espeak_executable():
|
| 200 |
+
executable = shutil.which("espeak-ng")
|
| 201 |
+
if executable is None:
|
| 202 |
+
raise RuntimeError("Install espeak-ng on the cloud machine before preprocessing/inference")
|
| 203 |
+
return executable
|
| 204 |
+
|
| 205 |
+
|
| 206 |
+
def espeak_version():
|
| 207 |
+
return subprocess.run([espeak_executable(), "--version"], capture_output=True, text=True, check=True, timeout=10).stdout.strip()
|
| 208 |
+
|
| 209 |
+
|
| 210 |
+
def espeak_words(piece, voice=None):
|
| 211 |
+
"""Phonemize one text piece. Returns words as lists of ``(phone, stress)``.
|
| 212 |
+
|
| 213 |
+
The input must end with a newline: eSpeak NG 1.51 silently drops the last
|
| 214 |
+
character of unterminated standard input.
|
| 215 |
+
"""
|
| 216 |
+
result = subprocess.run(
|
| 217 |
+
[espeak_executable(), "-q", "--ipa", "--sep=" + SEPARATOR, "-v", voice or ESPEAK_VOICE, "--stdin"],
|
| 218 |
+
input=piece.rstrip("\n") + "\n", text=True, capture_output=True, check=True, timeout=30)
|
| 219 |
+
return parse_espeak(result.stdout)
|
| 220 |
+
|
| 221 |
+
|
| 222 |
+
|
| 223 |
+
|
| 224 |
+
|
| 225 |
+
|
| 226 |
+
|
| 227 |
+
|
| 228 |
+
|
| 229 |
+
def parse_espeak(output):
|
| 230 |
+
words = []
|
| 231 |
+
for word in _LANGUAGE_TAG.sub("", output).split():
|
| 232 |
+
units = []
|
| 233 |
+
for unit in word.split(SEPARATOR):
|
| 234 |
+
stress = 0
|
| 235 |
+
for mark, level in STRESS_MARKS.items():
|
| 236 |
+
if mark in unit:
|
| 237 |
+
stress = stress or level
|
| 238 |
+
unit = unit.replace(mark, "")
|
| 239 |
+
unit = "".join(c for c in unit if unicodedata.category(c) != "Cf" and c not in "()")
|
| 240 |
+
if unit:
|
| 241 |
+
units.append((unit, stress))
|
| 242 |
+
if units:
|
| 243 |
+
words.append(units)
|
| 244 |
+
return words
|
| 245 |
+
|
| 246 |
+
|
| 247 |
+
def canonical(phone):
|
| 248 |
+
"""Map an eSpeak phoneme to inventory phones; ``None`` when unknown."""
|
| 249 |
+
if phone in PHONE_SET:
|
| 250 |
+
return (phone,)
|
| 251 |
+
if phone in FALLBACK:
|
| 252 |
+
return FALLBACK[phone]
|
| 253 |
+
stripped = "".join(c for c in unicodedata.normalize("NFD", phone) if not unicodedata.combining(c))
|
| 254 |
+
for candidate in (stripped, stripped.replace("ː", ""), stripped + "ː"):
|
| 255 |
+
if candidate != phone and candidate in PHONE_SET:
|
| 256 |
+
return (candidate,)
|
| 257 |
+
if candidate != phone and candidate in FALLBACK:
|
| 258 |
+
return FALLBACK[candidate]
|
| 259 |
+
return None
|
| 260 |
+
|
| 261 |
+
|
| 262 |
+
def tokenize(pieces):
|
| 263 |
+
"""Build the token sequence from ``(is_punctuation, value)`` pieces where a
|
| 264 |
+
text piece's value is the parsed eSpeak word list. Pure function (testable
|
| 265 |
+
without eSpeak)."""
|
| 266 |
+
symbols, stress, unknown = [BOS], [0], []
|
| 267 |
+
for punctuation, value in pieces:
|
| 268 |
+
if punctuation:
|
| 269 |
+
if symbols[-1] != value: # collapse repeats such as "!!"
|
| 270 |
+
symbols.append(value)
|
| 271 |
+
stress.append(0)
|
| 272 |
+
continue
|
| 273 |
+
for word in value:
|
| 274 |
+
if symbols[-1] in PHONE_SET or symbols[-1] == UNK:
|
| 275 |
+
symbols.append(SP)
|
| 276 |
+
stress.append(0)
|
| 277 |
+
for phone, level in word:
|
| 278 |
+
mapped = canonical(phone)
|
| 279 |
+
if mapped is None:
|
| 280 |
+
unknown.append(phone)
|
| 281 |
+
mapped = (UNK,)
|
| 282 |
+
# A fallback may expand to several phones: stress goes to its first vowel.
|
| 283 |
+
carrier = next((i for i, item in enumerate(mapped) if item in VOWEL_SET), 0)
|
| 284 |
+
for index, item in enumerate(mapped):
|
| 285 |
+
symbols.append(item)
|
| 286 |
+
stress.append(level if index == carrier else 0)
|
| 287 |
+
symbols.append(EOS)
|
| 288 |
+
stress.append(0)
|
| 289 |
+
if not any(s in PHONE_SET or s == UNK for s in symbols):
|
| 290 |
+
raise NothingToPronounce("the text has nothing to pronounce")
|
| 291 |
+
return Phonemized(tuple(symbols), tuple(SYMBOL_TO_ID[s] for s in symbols), tuple(stress), tuple(unknown))
|
| 292 |
+
|
| 293 |
+
|
| 294 |
+
LATIN_RUN = re.compile(r"[A-Za-z][A-Za-z']*")
|
| 295 |
+
|
| 296 |
+
def load_lexicon():
|
| 297 |
+
path = os.environ.get("TINY_VOCA_LEXICON")
|
| 298 |
+
if not path:
|
| 299 |
+
return {}
|
| 300 |
+
with open(path, encoding="utf-8") as f:
|
| 301 |
+
data = json.load(f)
|
| 302 |
+
return {str(k).lower(): str(v) for k, v in data.items()}
|
| 303 |
+
|
| 304 |
+
LEXICON = load_lexicon()
|
| 305 |
+
|
| 306 |
+
|
| 307 |
+
def espeak_mixed(piece):
|
| 308 |
+
'Phonemize Bengali text and route known Latin words through the Bengali lexicon.'
|
| 309 |
+
words = []
|
| 310 |
+
position = 0
|
| 311 |
+
|
| 312 |
+
for match in LATIN_RUN.finditer(piece):
|
| 313 |
+
prefix = piece[position:match.start()]
|
| 314 |
+
if prefix.strip():
|
| 315 |
+
words += espeak_words(prefix)
|
| 316 |
+
|
| 317 |
+
latin_word = match.group()
|
| 318 |
+
bengali_spelling = LEXICON.get(latin_word.casefold())
|
| 319 |
+
if bengali_spelling:
|
| 320 |
+
words += espeak_words(bengali_spelling, voice="bn")
|
| 321 |
+
else:
|
| 322 |
+
words += espeak_words(latin_word, voice="en-us")
|
| 323 |
+
|
| 324 |
+
position = match.end()
|
| 325 |
+
|
| 326 |
+
suffix = piece[position:]
|
| 327 |
+
if suffix.strip():
|
| 328 |
+
words += espeak_words(suffix)
|
| 329 |
+
|
| 330 |
+
return words
|
| 331 |
+
|
| 332 |
+
|
| 333 |
+
|
| 334 |
+
|
| 335 |
+
|
| 336 |
+
|
| 337 |
+
|
| 338 |
+
|
| 339 |
+
def phonemize(text):
|
| 340 |
+
if not isinstance(text, str) or not text.strip():
|
| 341 |
+
raise ValueError("text must not be empty")
|
| 342 |
+
if _frontend == "own":
|
| 343 |
+
return tokenize(_dizione().pieces(text))
|
| 344 |
+
pieces = []
|
| 345 |
+
for punctuation, piece in chunks(normalize_text(text)):
|
| 346 |
+
pieces.append((True, piece) if punctuation else (False, espeak_mixed(piece)))
|
| 347 |
+
return tokenize(pieces)
|
| 348 |
+
|
| 349 |
+
|
| 350 |
+
def is_phone(token_ids):
|
| 351 |
+
"""Boolean list/tensor helper: tokens that must be realised as audio."""
|
| 352 |
+
return [int(i) in PHONE_IDS for i in token_ids]
|