Hugging Face's logo

hillbyte
/
Indic-Lite

Text Classification
Joblib
ONNX
indic-nlp
language-identification
sentiment-analysis
Model card Files
xet
 Community
robzchhangte commited on
Commit
a55aad0
·
verified ·
1 Parent(s): 32a8422

Initial release of Indic-Lite: Zero-Annotation CPU Indic NLP Suite (LID, Sentiment, Topic, ONNX)

Browse files
Files changed (5) hide show
  1. BENCHMARK_REPORT.md +3 -3
  2. README.md +2 -0
  3. indic_lid_model.joblib +2 -2
  4. onnx/indic_lid.onnx +2 -2
  5. onnx/indic_lid_vocab.json +0 -0
BENCHMARK_REPORT.md CHANGED
@@ -6,9 +6,9 @@ Generated on an **AMD EPYC 16-core CPU System (Zero GPU required)**.
6
 
7
  | Model | Task / Coverage | Test Samples | Accuracy | Macro F1 | Disk Size | CPU Latency / Sample |
8
  |-----------------|-----------------------------------|----------------|------------|------------|-------------|------------------------|
9
- | Indic-LID | Language ID (26 languages) | 26,312 | 99.52% | 99.52% | 10.17 MB | 0.150 ms |
10
- | Indic-Sentiment | Sentiment Analysis (12 languages) | 10,129 | 75.84% | 75.84% | 1.64 MB | 0.163 ms |
11
- | Indic-Topic | News Categorization (6 topics) | 3,244 | 90.23% | 89.35% | 3.41 MB | 0.130 ms |
12
 
13
  ## Key Architectural Highlights
14
  - **Zero Manual Annotation**: Trained exclusively on openly licensed, pre-existing datasets.
 
6
 
7
  | Model | Task / Coverage | Test Samples | Accuracy | Macro F1 | Disk Size | CPU Latency / Sample |
8
  |-----------------|-----------------------------------|----------------|------------|------------|-------------|------------------------|
9
+ | Indic-LID | Language ID (26 languages) | 27,312 | 99.53% | 99.54% | 10.83 MB | 0.155 ms |
10
+ | Indic-Sentiment | Sentiment Analysis (12 languages) | 10,129 | 75.84% | 75.84% | 1.64 MB | 0.164 ms |
11
+ | Indic-Topic | News Categorization (6 topics) | 3,244 | 90.23% | 89.35% | 3.41 MB | 0.135 ms |
12
 
13
  ## Key Architectural Highlights
14
  - **Zero Manual Annotation**: Trained exclusively on openly licensed, pre-existing datasets.
README.md CHANGED
@@ -19,6 +19,8 @@ language:
19
  - brx
20
  - sat
21
  - gom
 
 
22
  - en
23
  license: cc-by-4.0
24
  tags:
 
19
  - brx
20
  - sat
21
  - gom
22
+ - lus
23
+ - kha
24
  - en
25
  license: cc-by-4.0
26
  tags:
indic_lid_model.joblib CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e3d6ad79e878911668a1d2bc25948cdc5d7248309c1d8feaa25f307aab123f2
3
- size 10665204
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1fa34c33734defd711e97b65c8dd4bedc2a2ee157dc4a244adb9b17c1426317
3
+ size 11360262
onnx/indic_lid.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:765ddd72d857dcf0225f7477395e9e7182d23b8fde11cc470d4563a2107eb263
3
- size 4161810
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1546878129cf11a8253d88e392159bb70980e95f86e6c0d9c7c97515eefe8d7
3
+ size 4481839
onnx/indic_lid_vocab.json CHANGED
The diff for this file is too large to render. See raw diff