salarymakage commited on
Commit ยท
68c3d3a
1
Parent(s): 520e23d
first version
Browse files- README.md +34 -0
- model.onnx +3 -0
- model_vocab.json +186 -0
README.md
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Model 9k (Small)
|
| 2 |
+
|
| 3 |
+
This directory contains a **lightweight** version of the **ThaoNet** recognition model, trained on approximately **9,000** samples (Khmer script).
|
| 4 |
+
|
| 5 |
+
## Model Architecture (`model-small`)
|
| 6 |
+
|
| 7 |
+
This model uses the **ThaoNet-Small** architecture, optimized for speed and low memory usage.
|
| 8 |
+
|
| 9 |
+
| Component | Setting | Notes |
|
| 10 |
+
|-----------|---------|-------|
|
| 11 |
+
| **Backbone** | `lightweight` | Use a 3-stage CNN (faster than ResNet). |
|
| 12 |
+
| **Head** | `transformer_ctc` | Shallow Transformer (2 layers, d=128). |
|
| 13 |
+
| **Input Size** | `32px` | Lower resolution for speed. |
|
| 14 |
+
| **Params** | **~1.6 Million** | Very small, suitable for mobile/CPU. |
|
| 15 |
+
|
| 16 |
+
## Usage
|
| 17 |
+
|
| 18 |
+
### 1. Run Inference (ONNX)
|
| 19 |
+
|
| 20 |
+
```bash
|
| 21 |
+
python tools/export/predict.py \
|
| 22 |
+
--onnx model9k/model.onnx \
|
| 23 |
+
--vocab model9k/model_vocab.json \
|
| 24 |
+
--image path/to/image.png \
|
| 25 |
+
--height 32
|
| 26 |
+
```
|
| 27 |
+
*Note: Ensure you use `--height 32` as this model was trained on lower resolution images.*
|
| 28 |
+
|
| 29 |
+
### 2. Performance & Data
|
| 30 |
+
* **Training Data**: 9,000 (9k) synthetic Khmer text line images.
|
| 31 |
+
* **CER (Character Error Rate)**: ~15-20% (Estimated on diverse data).
|
| 32 |
+
* **WER (Word Error Rate)**: ~30-40%.
|
| 33 |
+
* **Speed**: ~2-3x faster than the base model.
|
| 34 |
+
* **Accuracy**: Lower than `base` or `handwriting` models, especially on complex backgrounds. Best for simple, clean, printed text.
|
model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4944a3d0532703de08b2fe04f42fa74b1a0be8b36d5f16a6245643fee8b650a3
|
| 3 |
+
size 6596604
|
model_vocab.json
ADDED
|
@@ -0,0 +1,186 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"itos": [
|
| 3 |
+
"[BLANK]",
|
| 4 |
+
"[PAD]",
|
| 5 |
+
"A",
|
| 6 |
+
"B",
|
| 7 |
+
"C",
|
| 8 |
+
"D",
|
| 9 |
+
"E",
|
| 10 |
+
"F",
|
| 11 |
+
"G",
|
| 12 |
+
"H",
|
| 13 |
+
"I",
|
| 14 |
+
"J",
|
| 15 |
+
"K",
|
| 16 |
+
"L",
|
| 17 |
+
"M",
|
| 18 |
+
"N",
|
| 19 |
+
"O",
|
| 20 |
+
"P",
|
| 21 |
+
"Q",
|
| 22 |
+
"R",
|
| 23 |
+
"S",
|
| 24 |
+
"T",
|
| 25 |
+
"U",
|
| 26 |
+
"V",
|
| 27 |
+
"W",
|
| 28 |
+
"X",
|
| 29 |
+
"Y",
|
| 30 |
+
"Z",
|
| 31 |
+
"a",
|
| 32 |
+
"b",
|
| 33 |
+
"c",
|
| 34 |
+
"d",
|
| 35 |
+
"e",
|
| 36 |
+
"f",
|
| 37 |
+
"g",
|
| 38 |
+
"h",
|
| 39 |
+
"i",
|
| 40 |
+
"j",
|
| 41 |
+
"k",
|
| 42 |
+
"l",
|
| 43 |
+
"m",
|
| 44 |
+
"n",
|
| 45 |
+
"o",
|
| 46 |
+
"p",
|
| 47 |
+
"q",
|
| 48 |
+
"r",
|
| 49 |
+
"s",
|
| 50 |
+
"t",
|
| 51 |
+
"u",
|
| 52 |
+
"v",
|
| 53 |
+
"w",
|
| 54 |
+
"x",
|
| 55 |
+
"y",
|
| 56 |
+
"z",
|
| 57 |
+
"0",
|
| 58 |
+
"1",
|
| 59 |
+
"2",
|
| 60 |
+
"3",
|
| 61 |
+
"4",
|
| 62 |
+
"5",
|
| 63 |
+
"6",
|
| 64 |
+
"7",
|
| 65 |
+
"8",
|
| 66 |
+
"9",
|
| 67 |
+
".",
|
| 68 |
+
",",
|
| 69 |
+
"!",
|
| 70 |
+
"?",
|
| 71 |
+
"(",
|
| 72 |
+
")",
|
| 73 |
+
"[",
|
| 74 |
+
"]",
|
| 75 |
+
"-",
|
| 76 |
+
"+",
|
| 77 |
+
"/",
|
| 78 |
+
":",
|
| 79 |
+
";",
|
| 80 |
+
"\"",
|
| 81 |
+
"'",
|
| 82 |
+
" ",
|
| 83 |
+
"แ",
|
| 84 |
+
"แ",
|
| 85 |
+
"แ",
|
| 86 |
+
"แ",
|
| 87 |
+
"แ",
|
| 88 |
+
"แ
",
|
| 89 |
+
"แ",
|
| 90 |
+
"แ",
|
| 91 |
+
"แ",
|
| 92 |
+
"แ",
|
| 93 |
+
"แ",
|
| 94 |
+
"แ",
|
| 95 |
+
"แ",
|
| 96 |
+
"แ",
|
| 97 |
+
"แ",
|
| 98 |
+
"แ",
|
| 99 |
+
"แ",
|
| 100 |
+
"แ",
|
| 101 |
+
"แ",
|
| 102 |
+
"แ",
|
| 103 |
+
"แ",
|
| 104 |
+
"แ",
|
| 105 |
+
"แ",
|
| 106 |
+
"แ",
|
| 107 |
+
"แ",
|
| 108 |
+
"แ",
|
| 109 |
+
"แ",
|
| 110 |
+
"แ",
|
| 111 |
+
"แ",
|
| 112 |
+
"แ",
|
| 113 |
+
"แ",
|
| 114 |
+
"แ",
|
| 115 |
+
"แ ",
|
| 116 |
+
"แก",
|
| 117 |
+
"แข",
|
| 118 |
+
"แฃ",
|
| 119 |
+
"แค",
|
| 120 |
+
"แฅ",
|
| 121 |
+
"แฆ",
|
| 122 |
+
"แง",
|
| 123 |
+
"แจ",
|
| 124 |
+
"แฉ",
|
| 125 |
+
"แช",
|
| 126 |
+
"แซ",
|
| 127 |
+
"แฌ",
|
| 128 |
+
"แญ",
|
| 129 |
+
"แฎ",
|
| 130 |
+
"แฏ",
|
| 131 |
+
"แฐ",
|
| 132 |
+
"แฑ",
|
| 133 |
+
"แฒ",
|
| 134 |
+
"แณ",
|
| 135 |
+
"แถ",
|
| 136 |
+
"แท",
|
| 137 |
+
"แธ",
|
| 138 |
+
"แน",
|
| 139 |
+
"แบ",
|
| 140 |
+
"แป",
|
| 141 |
+
"แผ",
|
| 142 |
+
"แฝ",
|
| 143 |
+
"แพ",
|
| 144 |
+
"แฟ",
|
| 145 |
+
"แ",
|
| 146 |
+
"แ",
|
| 147 |
+
"แ",
|
| 148 |
+
"แ",
|
| 149 |
+
"แ",
|
| 150 |
+
"แ
",
|
| 151 |
+
"แ",
|
| 152 |
+
"แ",
|
| 153 |
+
"แ",
|
| 154 |
+
"แ",
|
| 155 |
+
"แ",
|
| 156 |
+
"แ",
|
| 157 |
+
"แ",
|
| 158 |
+
"แ",
|
| 159 |
+
"แ",
|
| 160 |
+
"แ",
|
| 161 |
+
"แ",
|
| 162 |
+
"แ",
|
| 163 |
+
"แ",
|
| 164 |
+
"แ ",
|
| 165 |
+
"แก",
|
| 166 |
+
"แข",
|
| 167 |
+
"แฃ",
|
| 168 |
+
"แค",
|
| 169 |
+
"แฅ",
|
| 170 |
+
"แฆ",
|
| 171 |
+
"แง",
|
| 172 |
+
"แจ",
|
| 173 |
+
"แฉ",
|
| 174 |
+
"แ",
|
| 175 |
+
"แ",
|
| 176 |
+
"แ",
|
| 177 |
+
"แ",
|
| 178 |
+
"แ",
|
| 179 |
+
"แ",
|
| 180 |
+
"แ",
|
| 181 |
+
"โ",
|
| 182 |
+
"โ",
|
| 183 |
+
"โ"
|
| 184 |
+
],
|
| 185 |
+
"blank_id": 0
|
| 186 |
+
}
|