@qvac/translation-nmtcpp 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/LICENSE +202 -0
- package/README.md +470 -0
- package/binding.js +1 -0
- package/index.d.ts +82 -0
- package/index.js +188 -0
- package/lib/error.js +65 -0
- package/marian.js +186 -0
- package/package.json +69 -0
- package/prebuilds/android-arm/qvac__translation-nmtcpp.bare +0 -0
- package/prebuilds/android-arm64/qvac__translation-nmtcpp.bare +0 -0
- package/prebuilds/android-ia32/qvac__translation-nmtcpp.bare +0 -0
- package/prebuilds/android-x64/qvac__translation-nmtcpp.bare +0 -0
- package/prebuilds/darwin-arm64/qvac__translation-nmtcpp.bare +0 -0
- package/prebuilds/darwin-arm64/qvac__translation-nmtcpp.bare.exports +3622 -0
- package/prebuilds/darwin-x64/qvac__translation-nmtcpp.bare +0 -0
- package/prebuilds/darwin-x64/qvac__translation-nmtcpp.bare.exports +3731 -0
- package/prebuilds/ios-arm64/qvac__translation-nmtcpp.bare +0 -0
- package/prebuilds/ios-arm64/qvac__translation-nmtcpp.bare.exports +3603 -0
- package/prebuilds/ios-arm64-simulator/qvac__translation-nmtcpp.bare +0 -0
- package/prebuilds/ios-arm64-simulator/qvac__translation-nmtcpp.bare.exports +3603 -0
- package/prebuilds/ios-x64-simulator/qvac__translation-nmtcpp.bare +0 -0
- package/prebuilds/ios-x64-simulator/qvac__translation-nmtcpp.bare.exports +3720 -0
- package/prebuilds/linux-x64/qvac__translation-nmtcpp.bare +0 -0
- package/prebuilds/win32-x64/qvac__translation-nmtcpp.bare +0 -0
- package/prebuilds/win32-x64/qvac__translation-nmtcpp.bare.exports +0 -0
- package/third-party/indic-processor-deps/indicnlp/INDIC_NLP_LICENCE +9 -0
- package/third-party/indic-processor-deps/indicnlp/index.js +11 -0
- package/third-party/indic-processor-deps/indicnlp/indic_detokenize.js +141 -0
- package/third-party/indic-processor-deps/indicnlp/indic_normalize.js +1213 -0
- package/third-party/indic-processor-deps/indicnlp/indic_tokenize.js +123 -0
- package/third-party/indic-processor-deps/indicnlp/langinfo.js +609 -0
- package/third-party/indic-processor-deps/indicnlp/sinhala_transliterator.js +197 -0
- package/third-party/indic-processor-deps/indicnlp/unicode_transliterator.js +120 -0
- package/third-party/indic-processor-deps/sacremoses/SACREMOSES_LICENCE +21 -0
- package/third-party/indic-processor-deps/sacremoses/cjk.js +202 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/README.txt +8 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.as +65 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.bn +65 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.ca +75 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.cs +390 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.de +325 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.el +1568 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.en +123 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.es +118 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.et +138 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.fi +138 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.fr +153 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.ga +48 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.gu +105 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.hi +113 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.hu +103 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.is +251 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.it +180 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.kn +70 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.lt +698 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.lv +100 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.ml +67 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.mni +65 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.mr +113 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.nl +115 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.or +101 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.pa +102 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.pl +283 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.pt +210 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.ro +38 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.ru +293 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.sk +474 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.sl +78 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.sv +97 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.ta +71 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.tdt +210 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.te +70 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.yue +53 -0
- package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.zh +53 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/CJK.txt +23246 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/CJKSymbols.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/Close_Punctuation.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/Currency_Symbol.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/Han.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/Hangul.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/Hangul_Syllables.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/Hiragana.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/IsAlnum-unichars-au.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/IsAlnum.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/IsAlpha-unichars-au.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/IsAlpha.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/IsLower.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/IsN.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/IsPf.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/IsPi.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/IsSc.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/IsSo.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/IsUpper.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/Katakana.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/Line_Separator.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/Lowercase_Letter.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/Number.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/Open_Punctuation.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/Punctuation.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/Separator.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/Symbol.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/Titlecase_Letter.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/data/perluniprops/Uppercase_Letter.txt +1 -0
- package/third-party/indic-processor-deps/sacremoses/index.js +8 -0
- package/third-party/indic-processor-deps/sacremoses/indic.js +76 -0
- package/third-party/indic-processor-deps/sacremoses/normalizer.js +264 -0
- package/third-party/indic-processor-deps/sacremoses/pernuliprops.js +287 -0
- package/third-party/indic-processor-deps/sacremoses/tokenizer.js +1217 -0
- package/third-party/indic-processor.js +565 -0
package/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.
|
package/README.md
ADDED
|
@@ -0,0 +1,470 @@
|
|
|
1
|
+
# Translation Addons
|
|
2
|
+
|
|
3
|
+
This library simplifies the process of running various translation models within [`QVAC`](#glossary) runtime applications. It provides a seamless interface to load, execute, and manage translation addons, offering support for multiple data sources (called data loaders).
|
|
4
|
+
|
|
5
|
+
## Table of Contents
|
|
6
|
+
|
|
7
|
+
- [Installation](#installation)
|
|
8
|
+
- [Usage](#usage)
|
|
9
|
+
- [1. Create DataLoader](#1-create-dataloader)
|
|
10
|
+
- [2. Create the `args` object](#2-create-the-args-object)
|
|
11
|
+
- [3. Create the `config` object](#3-create-the-config-object)
|
|
12
|
+
- [4. Create Model Instance](#4-create-model-instance)
|
|
13
|
+
- [5. Load Model](#5-load-model)
|
|
14
|
+
- [6. Run the Model](#6-run-the-model)
|
|
15
|
+
- [7. Unload the Model](#7-unload-the-model)
|
|
16
|
+
- [Quickstart Example](#quickstart-example)
|
|
17
|
+
- [Model Registry](#model-registry)
|
|
18
|
+
- [Supported Languages](#supported-languages)
|
|
19
|
+
- [ModelClasses and Packages](#modelclasses-and-packages)
|
|
20
|
+
- [Other Examples](#other-examples)
|
|
21
|
+
- [Glossary](#glossary)
|
|
22
|
+
- [Resources](#resources)
|
|
23
|
+
- [License](#license)
|
|
24
|
+
|
|
25
|
+
## Installation
|
|
26
|
+
|
|
27
|
+
### Prerequisites
|
|
28
|
+
|
|
29
|
+
Ensure that the [`Bare`](#glossary) Runtime is installed globally on your system. If it's not already installed, you can add it using:
|
|
30
|
+
|
|
31
|
+
```bash
|
|
32
|
+
npm i -g bare
|
|
33
|
+
```
|
|
34
|
+
|
|
35
|
+
> **Note:** Bare version must be **1.17.3 or higher**. Verify your version with:
|
|
36
|
+
|
|
37
|
+
```bash
|
|
38
|
+
bare -v
|
|
39
|
+
```
|
|
40
|
+
|
|
41
|
+
Before proceeding with the installation, please generate a **classic GitHub Personal Access Token (PAT)** with the `read:packages` scope. Once generated, add the token to your environment variables using the name `NPM_TOKEN`.
|
|
42
|
+
|
|
43
|
+
```bash
|
|
44
|
+
export NPM_TOKEN=your_personal_access_token
|
|
45
|
+
```
|
|
46
|
+
|
|
47
|
+
Next, create a `.npmrc` file in the root of your project with the following content:
|
|
48
|
+
|
|
49
|
+
```ini
|
|
50
|
+
@tetherto:registry=https://npm.pkg.github.com
|
|
51
|
+
//npm.pkg.github.com/:_authToken=${NPM_TOKEN}
|
|
52
|
+
```
|
|
53
|
+
|
|
54
|
+
This configuration ensures secure access to GitHub Packages when installing scoped packages.
|
|
55
|
+
|
|
56
|
+
### Installing the Package
|
|
57
|
+
|
|
58
|
+
Depending on your translation needs please choose an appropriate package from the [ModelClasses and Packages](#modelclasses-and-packages) Section and install it through `npm`. For example:
|
|
59
|
+
|
|
60
|
+
```bash
|
|
61
|
+
# For translating English to Italian
|
|
62
|
+
npm i @qvac/translation-nmtcpp
|
|
63
|
+
|
|
64
|
+
# For translation English to Hindi
|
|
65
|
+
npm i @tetherto/qvac-lib-inference-addon-mlc-indictrans2-en-indic-dist-200m-q0f32
|
|
66
|
+
```
|
|
67
|
+
|
|
68
|
+
## Usage
|
|
69
|
+
|
|
70
|
+
The library provides a straightforward and intuitive workflow for translating text. Irrespective of the chosen model, the workflow remains the same:
|
|
71
|
+
|
|
72
|
+
|
|
73
|
+
### 1. Create `DataLoader`
|
|
74
|
+
|
|
75
|
+
In QVAC, the [`DataLoader`](#glossary) class provides an interface for fetching model weights and other resources crucial for running AI Models. A `DataLoader` instance is required to successfully instantiate a `ModelClass`. We can create a [`HyperdriveDataLoader`](#glossary) using the following code.
|
|
76
|
+
|
|
77
|
+
```javascript
|
|
78
|
+
const HyperdriveDL = require('@qvac/dl-hyperdrive')
|
|
79
|
+
|
|
80
|
+
const hdDL = new HyperdriveDL({
|
|
81
|
+
key: 'hyperdrive-key-hex', // (Required) The Hyperdrive key containing model files.
|
|
82
|
+
store: corestore // (Optional) A Corestore instance. If not provided, Hyperdrive will use an in-memory store.
|
|
83
|
+
})
|
|
84
|
+
```
|
|
85
|
+
|
|
86
|
+
> **Note**: It is extremely important that you provide the correct `key` when using a `HyperdriveDataLoader`. A `DataLoader` with model weights and settings for an `en-it` translation can obviously not be utilized for doing a `de-en` translation. Please ensure that the `key` being used aligns with the model(package) installed and the translation requirement.
|
|
87
|
+
|
|
88
|
+
### 2. Create the `args` object
|
|
89
|
+
|
|
90
|
+
The `args` object contains the `DataLoader` we created in the previous step and other translation parameters that control how the translation model operates, including which languages to translate between and what performance metrics to collect.
|
|
91
|
+
|
|
92
|
+
```javascript
|
|
93
|
+
// Create arguments object with loader, translation parameters, and options
|
|
94
|
+
const args = {
|
|
95
|
+
// Required: Data loader instance
|
|
96
|
+
loader: hdDL, // or fsDL
|
|
97
|
+
|
|
98
|
+
// Required: Translation parameters
|
|
99
|
+
params: {
|
|
100
|
+
mode: 'full', // Model loading mode (full is recommended)
|
|
101
|
+
srcLang: 'en', // Source language (ISO 639-1 code)
|
|
102
|
+
dstLang: 'it' // Target language (ISO 639-1 code)
|
|
103
|
+
},
|
|
104
|
+
|
|
105
|
+
// Optional: Additional configuration
|
|
106
|
+
opts: {
|
|
107
|
+
stats: true // Enable performance statistics
|
|
108
|
+
}
|
|
109
|
+
}
|
|
110
|
+
```
|
|
111
|
+
|
|
112
|
+
> Note: The list of supported languages for the `srcLang` and `dstLang` parameters differ from one `ModelClass` to another. Please refer to the [Supported Languages](#supported-languages) section for more details.
|
|
113
|
+
|
|
114
|
+
### 3. Create the `config` object
|
|
115
|
+
|
|
116
|
+
This config expresses your “how to generate” policy for a run: it balances determinism (greedy/beam) and diversity (sampling) while enforcing simple constraints (length, repetition).
|
|
117
|
+
|
|
118
|
+
```javascript
|
|
119
|
+
// Define files needed by the model
|
|
120
|
+
const config = {
|
|
121
|
+
// Runtime decoding controls (can also be set later via model.setConfig)
|
|
122
|
+
beamsize: 4, // Beam search width (>=1). 1 disables beam search
|
|
123
|
+
lengthpenalty: 0.6, // Length normalization strength (>=0)
|
|
124
|
+
maxlength: 128, // Maximum generated tokens (>0)
|
|
125
|
+
|
|
126
|
+
// Repetition and constraints
|
|
127
|
+
repetitionpenalty: 1.2, // Penalize previously generated tokens (0..2)
|
|
128
|
+
norepeatngramsize: 2, // Disallow repeating n-grams of this size (0..10)
|
|
129
|
+
|
|
130
|
+
// Sampling controls
|
|
131
|
+
temperature: 0.8, //[0..2]
|
|
132
|
+
topk: 40, // Keep top-K logits [0..vocab_size]
|
|
133
|
+
topp: 0.9 // Nucleus sampling threshold (0< p <=1)
|
|
134
|
+
}
|
|
135
|
+
```
|
|
136
|
+
|
|
137
|
+
### 4. Create Model Instance
|
|
138
|
+
|
|
139
|
+
We first import the `ModelClass` from the installed package, then we instantiate the model by passing it the `args` and `config` objects.
|
|
140
|
+
|
|
141
|
+
```javascript
|
|
142
|
+
const { ModelClass } = require('installed/package/name')
|
|
143
|
+
const model = new ModelClass(args, config)
|
|
144
|
+
```
|
|
145
|
+
|
|
146
|
+
For example:
|
|
147
|
+
|
|
148
|
+
```javascript
|
|
149
|
+
const { MLCMarianOpusQ4F16 } = require('@qvac/translation-nmtcpp-opus-q4f16')
|
|
150
|
+
const model = new MLCMarianOpusQ4F16(args, config)
|
|
151
|
+
```
|
|
152
|
+
|
|
153
|
+
### 5. Load Model
|
|
154
|
+
|
|
155
|
+
```javascript
|
|
156
|
+
try {
|
|
157
|
+
// Basic usage
|
|
158
|
+
await model.load()
|
|
159
|
+
} catch (error) {
|
|
160
|
+
console.error('Failed to load model:', error)
|
|
161
|
+
}
|
|
162
|
+
```
|
|
163
|
+
|
|
164
|
+
### 6. Run the Model
|
|
165
|
+
|
|
166
|
+
We can perform inference on the input text using the `run()` method. This method returns a [`QVACResponse`](#glossary) object.
|
|
167
|
+
|
|
168
|
+
```javascript
|
|
169
|
+
try {
|
|
170
|
+
// Execute translation on input text
|
|
171
|
+
const response = await model.run('Hello world! Welcome to the internet of peers!')
|
|
172
|
+
|
|
173
|
+
// Process streamed output using callback
|
|
174
|
+
await response
|
|
175
|
+
.onUpdate(outputChunk => {
|
|
176
|
+
// Handle each new piece of translated text
|
|
177
|
+
console.log(outputChunk)
|
|
178
|
+
})
|
|
179
|
+
.await() // Wait for translation to complete
|
|
180
|
+
|
|
181
|
+
// Access performance statistics (if enabled with opts.stats)
|
|
182
|
+
if (response.stats) {
|
|
183
|
+
console.log('Translation completed in:', response.stats.totalTime, 'ms')
|
|
184
|
+
}
|
|
185
|
+
} catch (error) {
|
|
186
|
+
console.error('Translation failed:', error)
|
|
187
|
+
}
|
|
188
|
+
```
|
|
189
|
+
|
|
190
|
+
### 7. Unload the Model
|
|
191
|
+
|
|
192
|
+
```javascript
|
|
193
|
+
// Always unload the model when finished to free memory
|
|
194
|
+
try {
|
|
195
|
+
await model.unload()
|
|
196
|
+
} catch (error) {
|
|
197
|
+
console.error('Failed to unload model:', error)
|
|
198
|
+
}
|
|
199
|
+
```
|
|
200
|
+
|
|
201
|
+
### Additional Features
|
|
202
|
+
|
|
203
|
+
- **Pause and Resume:** Translation can be paused and resumed (see [`examples/pause.example.js`](examples/pause.example.js))
|
|
204
|
+
- **Progress Tracking:** Monitor loading progress with a callback function
|
|
205
|
+
- **Performance Stats:** Measure inference time with the `stats` option
|
|
206
|
+
|
|
207
|
+
For a complete working example that brings all these steps together, see the [Quickstart Example](#quickstart-example) below.
|
|
208
|
+
|
|
209
|
+
## Quickstart Example
|
|
210
|
+
|
|
211
|
+
Follow these steps to run the Quickstart Example:
|
|
212
|
+
|
|
213
|
+
### 1. Create a New Project
|
|
214
|
+
|
|
215
|
+
```bash
|
|
216
|
+
mkdir translation-example
|
|
217
|
+
cd translation-example
|
|
218
|
+
npm init -y
|
|
219
|
+
```
|
|
220
|
+
|
|
221
|
+
### 2. Install Required Dependencies
|
|
222
|
+
|
|
223
|
+
```bash
|
|
224
|
+
npm i @qvac/translation-nmtcpp-opus-q4f16 @qvac/dl-hyperdrive
|
|
225
|
+
```
|
|
226
|
+
|
|
227
|
+
### 3. Create `example.js` and paste the following code into it
|
|
228
|
+
|
|
229
|
+
```bash
|
|
230
|
+
touch example.js
|
|
231
|
+
```
|
|
232
|
+
|
|
233
|
+
```javascript
|
|
234
|
+
// example.js
|
|
235
|
+
|
|
236
|
+
'use strict'
|
|
237
|
+
|
|
238
|
+
// Note: This import will depend on the addon package installed
|
|
239
|
+
const TranslationNmtcpp = require('..')
|
|
240
|
+
const HyperdriveDL = require('@qvac/dl-hyperdrive')
|
|
241
|
+
|
|
242
|
+
const text = 'La traduzione automatica ha rivoluzionato il modo in cui comunichiamo attraverso le barriere linguistiche nel mondo digitale moderno.'
|
|
243
|
+
|
|
244
|
+
async function main () {
|
|
245
|
+
// 1. Create `DataLoader`
|
|
246
|
+
const hdDL = new HyperdriveDL({
|
|
247
|
+
// The hyperdrive key for en-it translation model weights and config
|
|
248
|
+
key: 'hd://9ef58f31c20d5556722e0b58a5d262fd89801daf2e6cb28e3f21ac6e9228088f'
|
|
249
|
+
})
|
|
250
|
+
|
|
251
|
+
// 2. Create the `args` object
|
|
252
|
+
const args = {
|
|
253
|
+
loader: hdDL,
|
|
254
|
+
params: { mode: 'full', dstLang: 'en', srcLang: 'it' },
|
|
255
|
+
diskPath: './models',
|
|
256
|
+
modelName: 'model.bin',
|
|
257
|
+
}
|
|
258
|
+
|
|
259
|
+
// 3. Optional : Create config object
|
|
260
|
+
const config = {beamsize : 4}
|
|
261
|
+
|
|
262
|
+
// 4. Create Model Instance
|
|
263
|
+
const model = new TranslationNmtcpp(args, config)
|
|
264
|
+
|
|
265
|
+
// 5. Load model
|
|
266
|
+
await model.load()
|
|
267
|
+
|
|
268
|
+
try {
|
|
269
|
+
// 6. Run the Model
|
|
270
|
+
const response = await model.run(text)
|
|
271
|
+
|
|
272
|
+
await response
|
|
273
|
+
.onUpdate(data => {
|
|
274
|
+
console.log(data)
|
|
275
|
+
})
|
|
276
|
+
.await()
|
|
277
|
+
|
|
278
|
+
console.log('translation finished!')
|
|
279
|
+
} finally {
|
|
280
|
+
// 7. Unload the model
|
|
281
|
+
await model.unload()
|
|
282
|
+
|
|
283
|
+
// Close the DataLoader
|
|
284
|
+
await hdDL.close()
|
|
285
|
+
}
|
|
286
|
+
}
|
|
287
|
+
|
|
288
|
+
|
|
289
|
+
main().catch(console.error)
|
|
290
|
+
```
|
|
291
|
+
|
|
292
|
+
### 4. Run the Example
|
|
293
|
+
|
|
294
|
+
```bash
|
|
295
|
+
bare example.js
|
|
296
|
+
```
|
|
297
|
+
|
|
298
|
+
You should see this output on successful execution
|
|
299
|
+
|
|
300
|
+
```bash
|
|
301
|
+
params_shard_0.bin has these many parameter records: 1
|
|
302
|
+
params_shard_1.bin has these many parameter records: 19
|
|
303
|
+
params_shard_2.bin has these many parameter records: 1
|
|
304
|
+
params_shard_3.bin has these many parameter records: 336
|
|
305
|
+
Ciao a tutti!
|
|
306
|
+
translation finished!
|
|
307
|
+
```
|
|
308
|
+
|
|
309
|
+
## Model Registry
|
|
310
|
+
|
|
311
|
+
The **Hyperbee key** for the model registry is:
|
|
312
|
+
|
|
313
|
+
```
|
|
314
|
+
7504626aaa534ac55d91b4b3067504774ae1457b03ddfbd86d817dd8cfbca8c8
|
|
315
|
+
```
|
|
316
|
+
|
|
317
|
+
Below is the section of the registry dedicated to **translation tasks**. Each entry maps a specific model and language pair (left-hand side) to the corresponding **Hyperdrive key** (right-hand side), which stores the model's weights and configuration settings.
|
|
318
|
+
|
|
319
|
+
```javascript
|
|
320
|
+
"translation:marian:opus-ggml:::q0f32:1.0.0:en-it": "9ef58f31c20d5556722e0b58a5d262fd89801daf2e6cb28e3f21ac6e9228088f"
|
|
321
|
+
"translation:marian:opus-ggml:::q0f32:1.0.0:en-de": "7b1d16235cd4dd9cc2c58d1fc1c41d65159aa4d2337169c6243a5bc8bf49689b"
|
|
322
|
+
"translation:marian:opus-ggml:::q0f32:1.0.0:en-es": "8aa823831cc55f5c1cba2c046e98b53a0d32376267ca73d653294b8b114459a2"
|
|
323
|
+
"translation:marian:opus-ggml:::q0f32:1.0.0:de-en": "b4d1ab62f885d9814acfddc565761b607bf86a307c38430ec1dabfe1a92532af"
|
|
324
|
+
"translation:marian:opus-ggml:::q0f32:1.0.0:de-es": "f432152db25ebd86fa0e48cd12f27e67e5c052c9af99c7662939dc1d84792c3e"
|
|
325
|
+
"translation:marian:opus-ggml:::q0f32:1.0.0:de-it": "06d26bdc965d548c156885ed105f8150618aaa11712579158e81f1d49735aaf6"
|
|
326
|
+
"translation:marian:opus-ggml:::q0f32:1.0.0:es-de": "ff6a02096c3e2f4e1aa7e4a75cb37aa851bc924c9d4af2b30b26431f1cb9d156"
|
|
327
|
+
"translation:marian:opus-ggml:::q0f32:1.0.0:es-en": "b96cf6c79119578b9f9a2206b19ce9686e95f31949ce62b24aef83fbdf4b0b08"
|
|
328
|
+
"translation:marian:opus-ggml:::q0f32:1.0.0:es-it": "b04ba8638fea5adff061aba9ccc671936ab8f7459346461f6c2010d4c7413254"
|
|
329
|
+
"translation:marian:opus-ggml:::q0f32:1.0.0:it-de": "438cbda449f1ac258a2fdea55cfd1f9f83dfb0ea20103c1e5113906081eec4f5"
|
|
330
|
+
"translation:marian:opus-ggml:::q0f32:1.0.0:it-en": "68778c8375fbb1e7f5c20b4e6087131206e9ddba1872655e20931b7e08fe3954"
|
|
331
|
+
"translation:marian:opus-ggml:::q0f32:1.0.0:it-es": "1b78d8309f80fcda61d0291ed5dc755e10e46b39d7e7484083a3c6d20b86c679"
|
|
332
|
+
"translation:ggml-indictrans:full:2:1B:q0f32:1.0.0:hi-en": "d46a9192b479fb5c982e60b84ae25bb5a61f3f090a41d45d5c5dda597973a9dd"
|
|
333
|
+
"translation:ggml-indictrans:full:2:1B:q0f32:1.0.0:en-hi": "61d1eb542956914ad2eadaf405b76a4dcc327fd6ccf1191bb17cd102a642691e"
|
|
334
|
+
"translation:ggml-indictrans:full:2:1B:q0f32:1.0.0:hi-hi": "cd8e441d1da68602e19a92f5d1ee794852e802ee234a638df2976bb1bc2493ad"
|
|
335
|
+
"translation:ggml-indictrans:dist:2:200M:q0f32:1.0.0:en-hi": "268c2e9b2a3420632e4b6649e32822f42d5dfbda4c7e96daec5b629ed20f99f7"
|
|
336
|
+
"translation:ggml-indictrans:dist:2:200M:q0f32:1.0.0:hi-en": "dfea395ffe1cb6d259029e5c81c290f8828981987855e23e7b66fd7c705901eb"
|
|
337
|
+
"translation:ggml-indictrans:dist:2:320M:q0f32:1.0.0:hi-hi": "9a66da960931c449b41e3315d9aea4d3925f2cda024e8a4c139b64d0a539ed41"
|
|
338
|
+
"translation:ggml-indictrans:full:2:1B:q0f16:1.0.0:en-hi": "be5bff40a002c627a992d096861c0e9b0be6ac7770300cee0bb09ccda87404cb"
|
|
339
|
+
"translation:ggml-indictrans:full:2:200M:q0f16:1.0.0:en-hi": "42ba45bbf4c24ff743890bc0cc65d8c23c91a14d26f760b3f814df76be8e036f"
|
|
340
|
+
"translation:ggml-indictrans:full:2:1B:q0f16:1.0.0:hi-en": "d06c487c56a36bb153d9d33bc1085bc90561d2a8dad5cd5701db782e1540a343"
|
|
341
|
+
"translation:ggml-indictrans:full:2:200M:q0f16:1.0.0:hi-en": "2e35d09ba69dd2b692c668862fdee43fa941859690b1e17aecc96c73474521b9"
|
|
342
|
+
"translation:ggml-indictrans:full:2:1B:q0f16:1.0.0:hi-hi": "f4edc8b072c34840c08aab2c8abdc288aa2dff8c2ed76fc96ad6604e322a038f"
|
|
343
|
+
"translation:ggml-indictrans:full:2:320M:q0f16:1.0.0:hi-hi": "1bb2ad463127325ca8daa801ec89ae6a2983ddeb90c5461a965e65fa295e3655"
|
|
344
|
+
"translation:ggml-indictrans:full:2:1B:q4_0:1.0.0:en-hi": "9fb5b7338504b24df0f3dd9ae8a1c280c6f00fd7f3295cca8f884514c5fa9713"
|
|
345
|
+
"translation:ggml-indictrans:full:2:200M:q4_0:1.0.0:en-hi": "8336d23073b2fd99723bf17d65ddc7b54b8ee886d6627659ba95c7a8fb932dc8"
|
|
346
|
+
"translation:ggml-indictrans:full:2:1B:q4_0:1.0.0:hi-en": "1fd66a6862776a92c7fae1962a1f07a5bc7369fb8be3dd9b76adf7c71855af7f"
|
|
347
|
+
"translation:ggml-indictrans:full:2:200M:q4_0:1.0.0:hi-en": "ba7db8c0dbcb6fc4276f86a27e3b9dd0f5e90b79f550a1666757f6074e2a4331"
|
|
348
|
+
"translation:ggml-indictrans:full:2:1B:q4_0:1.0.0:hi-hi": "0f03a3a06bc7006deb0da42643585dc0da49b897ba49e449ec67013ba4464e8a"
|
|
349
|
+
"translation:ggml-indictrans:full:2:320M:q4_0:1.0.0:hi-hi": "6cba73db82148a228bfdc586e2e565db6e6beb476575de3602d927ecb08b1a70"
|
|
350
|
+
```
|
|
351
|
+
|
|
352
|
+
Each key in this list follows the general pattern:
|
|
353
|
+
|
|
354
|
+
```
|
|
355
|
+
<model_family>:<version>:<size>:<quantization>:<release>:<source-lang>-<target-lang>
|
|
356
|
+
```
|
|
357
|
+
|
|
358
|
+
## Supported Languages
|
|
359
|
+
|
|
360
|
+
Here is the list of languages supported for the Marian models:
|
|
361
|
+
|
|
362
|
+
<table>
|
|
363
|
+
<tbody>
|
|
364
|
+
<tr><td>English (en)</td></tr>
|
|
365
|
+
<tr><td>German (de)</td></tr>
|
|
366
|
+
<tr><td>Italian (it)</td></tr>
|
|
367
|
+
<tr><td>Spanish (es)</td></tr>
|
|
368
|
+
</tbody>
|
|
369
|
+
</table>
|
|
370
|
+
|
|
371
|
+
Here is the list of languages supported by the IndicTrans2 models:
|
|
372
|
+
|
|
373
|
+
<table>
|
|
374
|
+
<tbody>
|
|
375
|
+
<tr>
|
|
376
|
+
<td>Assamese (asm_Beng)</td>
|
|
377
|
+
<td>Kashmiri (Arabic) (kas_Arab)</td>
|
|
378
|
+
<td>Punjabi (pan_Guru)</td>
|
|
379
|
+
</tr>
|
|
380
|
+
<tr>
|
|
381
|
+
<td>Bengali (ben_Beng)</td>
|
|
382
|
+
<td>Kashmiri (Devanagari) (kas_Deva)</td>
|
|
383
|
+
<td>Sanskrit (san_Deva)</td>
|
|
384
|
+
</tr>
|
|
385
|
+
<tr>
|
|
386
|
+
<td>Bodo (brx_Deva)</td>
|
|
387
|
+
<td>Maithili (mai_Deva)</td>
|
|
388
|
+
<td>Santali (sat_Olck)</td>
|
|
389
|
+
</tr>
|
|
390
|
+
<tr>
|
|
391
|
+
<td>Dogri (doi_Deva)</td>
|
|
392
|
+
<td>Malayalam (mal_Mlym)</td>
|
|
393
|
+
<td>Sindhi (Arabic) (snd_Arab)</td>
|
|
394
|
+
</tr>
|
|
395
|
+
<tr>
|
|
396
|
+
<td>English (eng_Latn)</td>
|
|
397
|
+
<td>Marathi (mar_Deva)</td>
|
|
398
|
+
<td>Sindhi (Devanagari) (snd_Deva)</td>
|
|
399
|
+
</tr>
|
|
400
|
+
<tr>
|
|
401
|
+
<td>Konkani (gom_Deva)</td>
|
|
402
|
+
<td>Manipuri (Bengali) (mni_Beng)</td>
|
|
403
|
+
<td>Tamil (tam_Taml)</td>
|
|
404
|
+
</tr>
|
|
405
|
+
<tr>
|
|
406
|
+
<td>Gujarati (guj_Gujr)</td>
|
|
407
|
+
<td>Manipuri (Meitei) (mni_Mtei)</td>
|
|
408
|
+
<td>Telugu (tel_Telu)</td>
|
|
409
|
+
</tr>
|
|
410
|
+
<tr>
|
|
411
|
+
<td>Hindi (hin_Deva)</td>
|
|
412
|
+
<td>Nepali (npi_Deva)</td>
|
|
413
|
+
<td>Urdu (urd_Arab)</td>
|
|
414
|
+
</tr>
|
|
415
|
+
<tr>
|
|
416
|
+
<td>Kannada (kan_Knda)</td>
|
|
417
|
+
<td>Odia (ory_Orya)</td>
|
|
418
|
+
<td></td>
|
|
419
|
+
</tr>
|
|
420
|
+
</tbody>
|
|
421
|
+
</table>
|
|
422
|
+
|
|
423
|
+
## Benchmarking
|
|
424
|
+
|
|
425
|
+
We conduct comprehensive benchmarking of our translation models to evaluate their performance across different language pairs and metrics. Our benchmarking suite measures translation quality using BLEU and COMET scores, as well as performance metrics including load times and inference speeds.
|
|
426
|
+
|
|
427
|
+
### Benchmark Results
|
|
428
|
+
|
|
429
|
+
For detailed benchmark results across all supported language pairs and model configurations, see our [Benchmark Results Summary](benchmarks/results/results_summary.md).
|
|
430
|
+
|
|
431
|
+
The benchmarking covers:
|
|
432
|
+
|
|
433
|
+
- **Translation Quality**: BLEU and COMET scores for accuracy assessment
|
|
434
|
+
- **Performance Metrics**: Model loading times and inference speeds
|
|
435
|
+
- **Language Pairs**: All supported source-target language combinations
|
|
436
|
+
- **Model Variants**: Different quantization levels and model sizes
|
|
437
|
+
|
|
438
|
+
Results are updated regularly as new model versions are released.
|
|
439
|
+
|
|
440
|
+
## Other Examples
|
|
441
|
+
|
|
442
|
+
- [Filesystem Data Loader](examples/example.fs.js): Demonstrates using the library with the Filesystem Data Loader for Marian model inference.
|
|
443
|
+
- [Pause Example](examples/pause.example.js): Demonstrates pausing and resuming the addon during inference.
|
|
444
|
+
- [IndicTrans2 en-hi Example](examples/indictrans.js): Demonstrates how to use the library for English-to-Hindi translation with the IndicTrans2 model, including setup, loading model weights, and running inference.
|
|
445
|
+
|
|
446
|
+
## Glossary
|
|
447
|
+
|
|
448
|
+
- **Bare** – Lightweight, modular JavaScript runtime for desktop and mobile. [Docs](https://docs.pears.com/bare-reference/overview)
|
|
449
|
+
- **Hyperdrive** – Secure, real-time distributed filesystem enabling P2P file sharing. [Docs](https://docs.pears.com/building-blocks/hyperdrive)
|
|
450
|
+
- **Hyperbee** – Decentralized B-tree built on Hypercores, with a key-value API. [Docs](https://docs.pears.com/building-blocks/hyperbee)
|
|
451
|
+
- **Corestore** – Factory for managing named collections of Hypercores. [Docs](https://docs.pears.com/helpers/corestore)
|
|
452
|
+
- **QVAC** – Open-source SDK for building decentralized AI applications.
|
|
453
|
+
- **QVACResponse** – The response object used by the QVAC API. [GitHub](https://github.com/tetherto/qvac-lib-response)
|
|
454
|
+
- **DataLoader** – Abstraction for fetching model weights and resources.
|
|
455
|
+
Implementations include:
|
|
456
|
+
- **`HyperdriveDL`** – Loads from a Hyperdrive instance [GitHub](https://github.com/tetherto/qvac-lib-dl-hyperdrive)
|
|
457
|
+
- **`fsDL`** – Loads from the local filesystem [GitHub](https://github.com/tetherto/qvac-lib-dl-filesystem)
|
|
458
|
+
|
|
459
|
+
## Resources
|
|
460
|
+
|
|
461
|
+
- **Pear Platform** – Decentralized platform for deploying apps. [pears.com](https://pears.com/)
|
|
462
|
+
- **Bare Runtime Docs** – For running QVAC apps in a lightweight environment. [docs.pears.com/bare](https://docs.pears.com/bare-reference/overview)
|
|
463
|
+
- **IndicTrans2 Model** – Pretrained multilingual translation models. [AI4Bharat/IndicTrans2](https://github.com/AI4Bharat/IndicTrans2)
|
|
464
|
+
- **Translation App Example** – QVAC-based translation application. [qvac-examples/translation-app](https://github.com/tetherto/qvac-examples/tree/main/translation-app)
|
|
465
|
+
|
|
466
|
+
## License
|
|
467
|
+
|
|
468
|
+
This project is licensed under the Apache-2.0 License - see the [LICENSE](LICENSE) file for details.<br>
|
|
469
|
+
For any questions o issues, please open an issue on the GitHub repository.
|
|
470
|
+
Test mobile job visibility
|
package/binding.js
ADDED
|
@@ -0,0 +1 @@
|
|
|
1
|
+
module.exports = require.addon()
|