failed09 commited on
Commit
32046bf
·
verified ·
1 Parent(s): 30d39c9

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. README.md +9 -1
  2. SHA256SUMS +1 -1
README.md CHANGED
@@ -86,6 +86,13 @@ For a local checkout with model files alongside `lid.py`,
86
  `LanguageIdentifier()` also works. The source project's `model/` layout
87
  remains supported.
88
 
 
 
 
 
 
 
 
89
  ## Training and Evaluation
90
 
91
  The model uses a dual-channel linear classifier trained for the BA/non-BA
@@ -110,7 +117,8 @@ short strings, names, OCR artifacts and mixed-language text can be ambiguous.
110
  Valid Bashkir text does not always contain Bashkir-specific letters. Empty
111
  strings and technical noise should be handled separately when filtering a
112
  corpus. For high-recall corpus construction, combine this model with the
113
- multiclass LID, dictionaries, quality rules and human review.
 
114
 
115
  ## License
116
 
 
86
  `LanguageIdentifier()` also works. The source project's `model/` layout
87
  remains supported.
88
 
89
+ ## Related Multilingual Model
90
+
91
+ Use this binary model when the main question is whether a sentence should pass
92
+ a Bashkir corpus gate. If you need to identify the predicted language, use the
93
+ companion [Bashkir Multiclass LID](https://huggingface.co/failed09/bashkir-lid-multiclass),
94
+ which distinguishes `ba`, `tt`, `ru` and `other`.
95
+
96
  ## Training and Evaluation
97
 
98
  The model uses a dual-channel linear classifier trained for the BA/non-BA
 
117
  Valid Bashkir text does not always contain Bashkir-specific letters. Empty
118
  strings and technical noise should be handled separately when filtering a
119
  corpus. For high-recall corpus construction, combine this model with the
120
+ [multiclass LID](https://huggingface.co/failed09/bashkir-lid-multiclass),
121
+ dictionaries, quality rules and human review.
122
 
123
  ## License
124
 
SHA256SUMS CHANGED
@@ -2,5 +2,5 @@ adbfcad591642c7a70aa39fbd53969502327aa2c5750507390557facae469742 model.onnx
2
  b9f3f823ce9fc7d22cca995915134d06dc4a31be61f08950751b94fc7a7b553d vectorizer.json
3
  a64200ae65f0d6449500ec35d4c74a5ed0c43e10902886add7aa3ef406a5724c lid.py
4
  839ecbad45a88253e2da2154e75744dd92ada5dbefdc3a68a83c8c1873865d1b config.json
5
- 666c6fb7d1773e570ec45e48420379b5e8d50f5b53800b52b237b42c7216aff3 README.md
6
  c06fea4773e32df0861cf38addf9426131480dcb5a45d36fbde8ba9de8fd851f META.json
 
2
  b9f3f823ce9fc7d22cca995915134d06dc4a31be61f08950751b94fc7a7b553d vectorizer.json
3
  a64200ae65f0d6449500ec35d4c74a5ed0c43e10902886add7aa3ef406a5724c lid.py
4
  839ecbad45a88253e2da2154e75744dd92ada5dbefdc3a68a83c8c1873865d1b config.json
5
+ bdc7e484e09fd4bbad81e6e05d0e11c7fb86a88f7c97a7383f6e9c14d6d66639 README.md
6
  c06fea4773e32df0861cf38addf9426131480dcb5a45d36fbde8ba9de8fd851f META.json