Upload README.md with huggingface_hub

README.md

@@ -1,6 +1,5 @@
 ---
 language:
-  - zh
   - en
 license: agpl-3.0
 tags:
@@ -15,7 +14,7 @@ metrics:
   - name: "validation accuracy"
     type: accuracy
     value: 0.886
-  - name: "real login success (per-attempt)"
+  - name: "per-attempt login success"
     type: accuracy
     value: 0.876
   - name: "login success with retries"
@@ -25,28 +24,19 @@ metrics:
 
 # PHPWind Captcha OCR
 
-**中文**：识别 PHPWind 论坛内置验证码的 OCR 模型（4 位数字）。完全本地推理，无外部 API 依赖，4 MB。
-**English**: An OCR model for the built-in PHPWind forum captcha (4 digits). Fully local inference, no external API, 4 MB.
+An OCR model for the built-in **PHPWind forum captcha** (4 digits). Fully local inference, no external API, 4 MB ONNX model.
 
----
-
-## 识别对象 / What it recognizes
-
-**中文**：下面这类 PHPWind 论坛登录验证码（彩色数字 + 干扰线）：
-**English**: The PHPWind forum login captcha (colored digits + noise lines):
+**中文版**: [README_zh.md](README_zh.md)
 
 ![example captcha](assets/example_captcha.png)
 
 ```
-示例输入 (example input)  →  模型输出 (model output): 9125
+Example input  →  Model output: 9125
 ```
 
-**中文**：验证码是 PHPWind 内置组件（`PwVerifyCode` / `PwGDCode`），彩色数字、干扰线、扭曲均为其标准特征。
-**English**: This is PHPWind's built-in captcha component (`PwVerifyCode`/`PwGDCode`) — colored digits, noise lines and distortion are its standard features.
-
----
+This captcha is PHPWind's built-in component (`PwVerifyCode` / `PwGDCode`). Colored digits, noise lines and distortion are its standard features.
 
-## 快速使用 / Quick Start
+## Quick Start
 
 ### Python (onnxruntime)
 
@@ -74,59 +64,38 @@ print(solve("captcha.png"))   # e.g. "9125"
 
 See [docs/INFERENCE.md](docs/INFERENCE.md).
 
----
-
-## 输入 / 输出规格 (I/O spec)
+## I/O Specification
 
-| 中文 | English |
+| Item | Spec |
 |---|---|
-| 输入 `input`：`[batch, 3, 64, 160]` float32 (RGB, [0,1]) | Input `input`: `[batch, 3, 64, 160]` float32 (RGB, [0,1]) |
-| 输出 `logits`：`[batch, 4, 10]`，每位置 argmax → 数字 | Output `logits`: `[batch, 4, 10]`, argmax per position → digit |
-| ONNX opset 18 | ONNX opset 18 |
-| 预处理：RGB → 160x64 (BILINEAR) → /255 | Preprocess: RGB → 160x64 (BILINEAR) → /255 |
-
----
+| Input `input` | `[batch, 3, 64, 160]` float32, RGB, values in `[0, 1]` |
+| Output `logits` | `[batch, 4, 10]`, argmax per position → digit |
+| ONNX opset | 18 |
+| Preprocessing | RGB → resize 160x64 (BILINEAR) → divide by 255 |
 
-## 评估结果 / Evaluation
+## Evaluation
 
-**中文**：用真实论坛登录作为 ground truth（登录成功 = 识别正确）。
-**English**: Evaluated against real forum logins (login success = correct recognition).
+Evaluated against **real forum logins** (login success = correct recognition). Details in [docs/EVALUATION.md](docs/EVALUATION.md).
 
-| 指标 / Metric | 数值 / Value |
+| Metric | Value |
 |---|---|
-| 验证集精度 / Validation accuracy | 88.6% |
-| 真实登录单次命中 / Per-attempt login success | **87.6%** (85/97) |
-| 带重试登录成功率 / With retries | ≈99.9997% |
+| Validation accuracy | 88.6% |
+| Per-attempt login success | **87.6%** (85/97) |
+| Login success with retries | ≈99.9997% |
 
-**中文**：详情见 [docs/EVALUATION.md](docs/EVALUATION.md)。
-**English**: Details in [docs/EVALUATION.md](docs/EVALUATION.md).
+## Training & Fine-tuning
 
----
-
-## 训练 / 微调 (Training & Fine-tuning)
-
-**中文**：997 张人工标注验证码，CNN 从零训练（位置保留架构）。
-**English**: 997 manually-labeled captchas, CNN trained from scratch (position-preserving architecture).
-
-- 数据 / Data: `data/` (997 labeled images)
-- 脚本 / Scripts: `scripts/train_fixed.py`
-- 指南 / Guide: [docs/TRAINING.md](docs/TRAINING.md)
+997 manually-labeled captchas, CNN trained from scratch with a position-preserving architecture.
 
----
-
-## 说明 / Notes
+- Data: `data/` (997 labeled images)
+- Script: `scripts/train_fixed.py`
+- Guide: [docs/TRAINING.md](docs/TRAINING.md)
 
-**中文**：
-- 验证码为 PHPWind 内置组件（非站点定制）。
-- 不同 PHPWind 版本参数可能有差异，换站使用前建议对比样例确认风格。
+## Notes
 
-**English**:
 - The captcha is PHPWind's built-in component (not site-custom).
-- Different PHPWind versions may differ; compare samples before use on another site.
-
----
+- Different PHPWind versions may differ; compare samples before using on another site.
 
-## 许可证 / License
+## License
 
-**中文**：本模型采用 **GNU AGPL-3.0** 许可 —— 可自由使用、修改、分发（含商用），但修改版/衍生作品必须同样以 AGPL 开源；网络服务使用也需提供源码。详见 [LICENSE](LICENSE)。
-**English**: Licensed under the **GNU AGPL-3.0** — free to use, modify and distribute (including commercial use), provided modified/derivative works stay AGPL-licensed; network-server use must offer source. See [LICENSE](LICENSE).
+GNU AGPL-3.0 — free to use, modify and distribute (including commercial use), provided modified/derivative works stay AGPL-licensed; network-server use must offer source. See [LICENSE](LICENSE).