Delete READ.md
Browse files
READ.md
DELETED
|
@@ -1,22 +0,0 @@
|
|
| 1 |
-
# Model
|
| 2 |
-
|
| 3 |
-
The `segment-any-text/sat-12l-sm` model is a part of the Segment Any Text (SAT) framework, specifically utilized within the [WTPSplit](https://github.com/segment-any-text/wtpsplit/) project. This model enables efficient and flexible text segmentation by leveraging `XML-Roberta` architectures.
|
| 4 |
-
|
| 5 |
-
# Available Model Types
|
| 6 |
-
|
| 7 |
-
We provide multiple formats of the `sat-12l-sm` model:
|
| 8 |
-
|
| 9 |
-
### ONNX
|
| 10 |
-
|
| 11 |
-
1. Default: Standard ONNX model for general use.
|
| 12 |
-
2. Optimized: Performance-enhanced version with improved inference speed.
|
| 13 |
-
|
| 14 |
-
### TensorRT
|
| 15 |
-
|
| 16 |
-
1. FP32: Floating-point precision model, ensuring high accuracy.
|
| 17 |
-
2. FP32+INT8: Mixed precision (FP32 and INT8) model for optimized inference speed with reduced memory footprint.
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
# Reference
|
| 21 |
-
1. [Github](https://github.com/pytheralab/sati/tree/main)
|
| 22 |
-
2. [Library and the WtP models](https://github.com/segment-any-text/wtpsplit)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|