Automatic Speech Recognition
NeMo
Persian
speech
persian
farsi
fastconformer
ctc
on-device
shenava
shenava-1
visualears
liteasr
compression
low-rank
dhh
Instructions to use PersianML/Shenava-Koochik-Lite-v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use PersianML/Shenava-Koochik-Lite-v1.0 with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("PersianML/Shenava-Koochik-Lite-v1.0") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Mirror Reza2kn/Shenava-Koochik-Lite-v1.0 at revision b20f2223ba15b8f4df13a95885710c4eee1a2c0a
Browse files- LICENSE +202 -0
- README.md +80 -0
- koochik_lite099_enc.pt +3 -0
- koochik_lite099_kmap.json +1 -0
- load_koochik_lite.py +48 -0
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.
|
README.md
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- fa
|
| 5 |
+
library_name: nemo
|
| 6 |
+
pipeline_tag: automatic-speech-recognition
|
| 7 |
+
tags:
|
| 8 |
+
- nemo
|
| 9 |
+
- automatic-speech-recognition
|
| 10 |
+
- speech
|
| 11 |
+
- persian
|
| 12 |
+
- farsi
|
| 13 |
+
- fastconformer
|
| 14 |
+
- ctc
|
| 15 |
+
- on-device
|
| 16 |
+
- shenava
|
| 17 |
+
- shenava-1
|
| 18 |
+
- visualears
|
| 19 |
+
- liteasr
|
| 20 |
+
- compression
|
| 21 |
+
- low-rank
|
| 22 |
+
- dhh
|
| 23 |
+
base_model: Reza2kn/Shenava-Koochik-v1.0
|
| 24 |
+
base_model_relation: quantized
|
| 25 |
+
datasets:
|
| 26 |
+
- Reza2kn/visualears-golden-6669
|
| 27 |
+
- Reza2kn/fleurs-fa-benchmark
|
| 28 |
+
---
|
| 29 |
+
|
| 30 |
+
# Shenava Koochik Lite v1.0
|
| 31 |
+
|
| 32 |
+
A LITEASR-compressed encoder for [Shenava Koochik v1.0](https://huggingface.co/Reza2kn/Shenava-Koochik-v1.0). Post-training low-rank factorization reduces the encoder from 108.9M to 85.4M parameters (21.6%) without retraining.
|
| 33 |
+
|
| 34 |
+
This repository is **not a standalone ASR checkpoint**. It contains a replacement encoder state dict and must be loaded on top of the base `.nemo` model; the decoder, CTC head, and tokenizer still come from Koochik.
|
| 35 |
+
|
| 36 |
+
- Canonical repository: [`Reza2kn/Shenava-Koochik-Lite-v1.0`](https://huggingface.co/Reza2kn/Shenava-Koochik-Lite-v1.0)
|
| 37 |
+
- PersianML mirror: [`PersianML/Shenava-Koochik-Lite-v1.0`](https://huggingface.co/PersianML/Shenava-Koochik-Lite-v1.0)
|
| 38 |
+
|
| 39 |
+
## Files
|
| 40 |
+
|
| 41 |
+
- `koochik_lite099_enc.pt`: compressed FP32 encoder state dict.
|
| 42 |
+
- `koochik_lite099_kmap.json`: retained rank for each factorized layer.
|
| 43 |
+
- `load_koochik_lite.py`: reconstructs the low-rank modules and loads the state dict into the base model.
|
| 44 |
+
|
| 45 |
+
## Load
|
| 46 |
+
|
| 47 |
+
```python
|
| 48 |
+
from huggingface_hub import hf_hub_download, snapshot_download
|
| 49 |
+
from load_koochik_lite import load_koochik_lite
|
| 50 |
+
|
| 51 |
+
base = hf_hub_download(
|
| 52 |
+
"Reza2kn/Shenava-Koochik-v1.0",
|
| 53 |
+
"shenava-koochik-v1.0.nemo",
|
| 54 |
+
)
|
| 55 |
+
repo = snapshot_download("Reza2kn/Shenava-Koochik-Lite-v1.0")
|
| 56 |
+
model = load_koochik_lite(
|
| 57 |
+
base,
|
| 58 |
+
f"{repo}/koochik_lite099_enc.pt",
|
| 59 |
+
f"{repo}/koochik_lite099_kmap.json",
|
| 60 |
+
)
|
| 61 |
+
print(model.transcribe(["speech.wav"])[0].text)
|
| 62 |
+
```
|
| 63 |
+
|
| 64 |
+
## Published trade-off
|
| 65 |
+
|
| 66 |
+
The release evaluated both greedy decoding and an optional Vosk-guided hotword beam. Lower is better.
|
| 67 |
+
|
| 68 |
+
| Decode | golden-6669 keyword-band WER | FLEURS keyword-band WER | golden-6669 overall WER | FLEURS overall WER |
|
| 69 |
+
|---|---:|---:|---:|---:|
|
| 70 |
+
| Full Koochik, greedy | 8.0 | 13.1 | 4.64 | 5.36 |
|
| 71 |
+
| Koochik Lite, greedy | 12.5 | 18.0 | 6.92 | 7.23 |
|
| 72 |
+
| Koochik Lite + Vosk guide | 6.4 | 11.7 | 5.30 | 5.31 |
|
| 73 |
+
|
| 74 |
+
Compression alone reduces quality; the Vosk-guided result requires a separate Vosk first pass plus hotword-aware `pyctcdecode` beam search. Do not compare the guided row to a greedy-only deployment as though they used the same runtime.
|
| 75 |
+
|
| 76 |
+
## فارسی
|
| 77 |
+
|
| 78 |
+
این مخزن یک مدل کامل و مستقل نیست؛ فقط encoder فشردهشده را نگه میدارد و برای اجرا به فایل NeMo مدل اصلی نیاز دارد. نسخهٔ greedy سبکتر است ولی افت دقت دارد؛ ردیف Vosk-guided به یک مرحلهٔ جداگانهٔ Vosk و beam search نیاز دارد.
|
| 79 |
+
|
| 80 |
+
Apache-2.0. Compression method: [LITEASR](https://arxiv.org/abs/2502.20583).
|
koochik_lite099_enc.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6ea7af0b1428160d3d74b242fb1f0bd95a4f548bc4b43775dc20ff1766c884b
|
| 3 |
+
size 341748739
|
koochik_lite099_kmap.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"layers.0.feed_forward1.linear1": 208, "layers.0.feed_forward1.linear2": 352, "layers.0.self_attn.linear_q": 208, "layers.0.self_attn.linear_k": 160, "layers.0.self_attn.linear_v": 160, "layers.0.self_attn.linear_out": 176, "layers.0.self_attn.linear_pos": 32, "layers.0.feed_forward2.linear1": 256, "layers.0.feed_forward2.linear2": 400, "layers.1.feed_forward1.linear1": 256, "layers.1.feed_forward1.linear2": 336, "layers.1.self_attn.linear_q": 208, "layers.1.self_attn.linear_k": 160, "layers.1.self_attn.linear_v": 240, "layers.1.self_attn.linear_pos": 48, "layers.1.feed_forward2.linear1": 288, "layers.2.feed_forward1.linear1": 288, "layers.2.feed_forward1.linear2": 304, "layers.2.self_attn.linear_q": 240, "layers.2.self_attn.linear_k": 192, "layers.2.self_attn.linear_v": 240, "layers.2.self_attn.linear_pos": 32, "layers.2.feed_forward2.linear1": 288, "layers.3.feed_forward1.linear1": 304, "layers.3.feed_forward1.linear2": 368, "layers.3.self_attn.linear_q": 240, "layers.3.self_attn.linear_k": 176, "layers.3.self_attn.linear_pos": 32, "layers.3.feed_forward2.linear1": 304, "layers.4.feed_forward1.linear1": 288, "layers.4.feed_forward1.linear2": 64, "layers.4.self_attn.linear_q": 240, "layers.4.self_attn.linear_k": 192, "layers.4.self_attn.linear_out": 240, "layers.4.self_attn.linear_pos": 32, "layers.4.feed_forward2.linear1": 288, "layers.5.feed_forward1.linear1": 288, "layers.5.feed_forward1.linear2": 304, "layers.5.self_attn.linear_q": 224, "layers.5.self_attn.linear_k": 176, "layers.5.self_attn.linear_out": 208, "layers.5.self_attn.linear_pos": 32, "layers.5.feed_forward2.linear1": 272, "layers.6.feed_forward1.linear1": 272, "layers.6.feed_forward1.linear2": 320, "layers.6.self_attn.linear_q": 224, "layers.6.self_attn.linear_k": 176, "layers.6.self_attn.linear_v": 240, "layers.6.self_attn.linear_out": 240, "layers.6.self_attn.linear_pos": 32, "layers.6.feed_forward2.linear1": 256, "layers.7.feed_forward1.linear1": 272, "layers.7.feed_forward1.linear2": 240, "layers.7.self_attn.linear_q": 208, "layers.7.self_attn.linear_k": 160, "layers.7.self_attn.linear_out": 240, "layers.7.self_attn.linear_pos": 32, "layers.7.feed_forward2.linear1": 256, "layers.8.feed_forward1.linear1": 272, "layers.8.feed_forward1.linear2": 96, "layers.8.self_attn.linear_q": 224, "layers.8.self_attn.linear_k": 176, "layers.8.self_attn.linear_v": 240, "layers.8.self_attn.linear_out": 240, "layers.8.self_attn.linear_pos": 32, "layers.8.feed_forward2.linear1": 272, "layers.9.feed_forward1.linear1": 288, "layers.9.feed_forward1.linear2": 384, "layers.9.self_attn.linear_q": 224, "layers.9.self_attn.linear_k": 192, "layers.9.self_attn.linear_pos": 32, "layers.9.feed_forward2.linear1": 272, "layers.10.feed_forward1.linear1": 288, "layers.10.feed_forward1.linear2": 336, "layers.10.self_attn.linear_q": 224, "layers.10.self_attn.linear_k": 208, "layers.10.self_attn.linear_pos": 32, "layers.10.feed_forward2.linear1": 272, "layers.11.feed_forward1.linear1": 304, "layers.11.feed_forward1.linear2": 304, "layers.11.self_attn.linear_k": 224, "layers.11.self_attn.linear_pos": 32, "layers.11.feed_forward2.linear1": 288, "layers.12.feed_forward1.linear1": 336, "layers.12.feed_forward1.linear2": 368, "layers.12.self_attn.linear_k": 240, "layers.12.self_attn.linear_pos": 32, "layers.12.feed_forward2.linear1": 320, "layers.12.feed_forward2.linear2": 400, "layers.13.feed_forward1.linear1": 352, "layers.13.feed_forward1.linear2": 144, "layers.13.self_attn.linear_q": 240, "layers.13.self_attn.linear_k": 224, "layers.13.self_attn.linear_pos": 32, "layers.13.feed_forward2.linear1": 320, "layers.13.feed_forward2.linear2": 336, "layers.14.feed_forward1.linear1": 320, "layers.14.feed_forward1.linear2": 16, "layers.14.self_attn.linear_q": 240, "layers.14.self_attn.linear_k": 224, "layers.14.self_attn.linear_pos": 48, "layers.14.feed_forward2.linear1": 320, "layers.14.feed_forward2.linear2": 400, "layers.15.feed_forward1.linear1": 304, "layers.15.feed_forward1.linear2": 16, "layers.15.self_attn.linear_q": 240, "layers.15.self_attn.linear_k": 224, "layers.15.self_attn.linear_pos": 48, "layers.15.feed_forward2.linear1": 288, "layers.15.feed_forward2.linear2": 320, "layers.16.feed_forward1.linear1": 288, "layers.16.self_attn.linear_q": 240, "layers.16.self_attn.linear_k": 224, "layers.16.self_attn.linear_pos": 32, "layers.16.feed_forward2.linear1": 320, "layers.16.feed_forward2.linear2": 352}
|
load_koochik_lite.py
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python3
|
| 2 |
+
"""Load Shenava-Koochik-Lite-v1.0 — a LITEASR-compressed (-21.6% encoder) Koochik.
|
| 3 |
+
|
| 4 |
+
Needs the base model Reza2kn/Shenava-Koochik-v1.0 (.nemo) plus this repo's
|
| 5 |
+
`koochik_lite099_enc.pt` (compressed encoder state_dict) and `koochik_lite099_kmap.json`
|
| 6 |
+
(per-layer low-rank sizes k). LITEASR replaces each targeted encoder Linear with a
|
| 7 |
+
rank-k Sequential(Linear(D_in->k, bias=False), Linear(k->D_out, bias=True)); this loader
|
| 8 |
+
rebuilds that skeleton from the kmap, then loads the compressed weights.
|
| 9 |
+
|
| 10 |
+
from huggingface_hub import hf_hub_download, snapshot_download
|
| 11 |
+
base = hf_hub_download("Reza2kn/Shenava-Koochik-v1.0", "shenava-koochik-v1.0.nemo")
|
| 12 |
+
repo = snapshot_download("Reza2kn/Shenava-Koochik-Lite-v1.0")
|
| 13 |
+
from load_koochik_lite import load_koochik_lite
|
| 14 |
+
m = load_koochik_lite(base, f"{repo}/koochik_lite099_enc.pt", f"{repo}/koochik_lite099_kmap.json")
|
| 15 |
+
print(m.transcribe(["clip.wav"])[0].text)
|
| 16 |
+
"""
|
| 17 |
+
import json, torch, torch.nn as nn
|
| 18 |
+
import nemo.collections.asr as A
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
def load_koochik_lite(base_nemo, enc_sd_path, kmap_path, device="cuda", ctc=True):
|
| 22 |
+
m = A.models.ASRModel.restore_from(base_nemo, map_location=device).eval()
|
| 23 |
+
if ctc:
|
| 24 |
+
try:
|
| 25 |
+
m.change_decoding_strategy(decoder_type="ctc")
|
| 26 |
+
except Exception:
|
| 27 |
+
pass
|
| 28 |
+
|
| 29 |
+
def parent(root, name):
|
| 30 |
+
parts = name.split("."); p = root
|
| 31 |
+
for x in parts[:-1]:
|
| 32 |
+
p = getattr(p, x)
|
| 33 |
+
return p, parts[-1]
|
| 34 |
+
|
| 35 |
+
for n, k in json.load(open(kmap_path)).items():
|
| 36 |
+
par, at = parent(m.encoder, n)
|
| 37 |
+
mod = getattr(par, at)
|
| 38 |
+
Dout, Din = mod.weight.shape
|
| 39 |
+
setattr(par, at, nn.Sequential(nn.Linear(Din, k, bias=False), nn.Linear(k, Dout, bias=True)))
|
| 40 |
+
m.encoder.load_state_dict(torch.load(enc_sd_path, map_location=device), strict=True)
|
| 41 |
+
return m.to(device).eval()
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
if __name__ == "__main__":
|
| 45 |
+
import sys
|
| 46 |
+
m = load_koochik_lite(sys.argv[1], sys.argv[2], sys.argv[3], device="cuda" if torch.cuda.is_available() else "cpu")
|
| 47 |
+
for r in m.transcribe(sys.argv[4:], batch_size=8):
|
| 48 |
+
print(r.text if hasattr(r, "text") else r)
|