From b164779af410227920a02d6e22050f52317d535b Mon Sep 17 00:00:00 2001
From: jhqxxx <18280426169@163.com>
Date: Sat, 6 Jun 2026 18:45:40 +0800
Subject: [PATCH] update doc
---
README.zh-CN.md | 2 +-
docs/supported-models.md | 5 +++--
docs/supported-models.zh-CN.md | 5 +++--
src/cli/mod.rs | 4 +---
src/models/mod.rs | 4 +---
5 files changed, 9 insertions(+), 11 deletions(-)
diff --git a/README.zh-CN.md b/README.zh-CN.md
index be413a8..f85dacc 100644
--- a/README.zh-CN.md
+++ b/README.zh-CN.md
@@ -34,7 +34,7 @@ aha 是一款基于 Rust 和 Candle 框架构建的高性能跨平台 AI 推理
|------|------|
| **文本** | Qwen3, MiniCPM4, MiniCPM5, LFM2, LFM2.5 |
| **视觉** | Qwen2.5-VL, Qwen3-VL, Qwen3.5
LFM2.5-VL, LFM2-VL |
-| **OCR** | DeepSeek-OCR, DeepSeek-OCR-2, PaddleOCR-VL,
PaddleOCR-VL1.5, Hunyuan-OCR, GLM-OCR |
+| **OCR** | DeepSeek-OCR, DeepSeek-OCR-2, PaddleOCR-VL,
PaddleOCR-VL1.5, PaddleOCR-VL1.5, Hunyuan-OCR
GLM-OCR |
| **ASR** | GLM-ASR-Nano, Fun-ASR-Nano, Qwen3-ASR |
| **TTS** | VoxCPM, VoxCPM1.5, VoxCPM2, Moss-TTS-Nano |
| **图像** | RMBG-2.0 (背景移除) |
diff --git a/docs/supported-models.md b/docs/supported-models.md
index e3efc61..e2b8250 100644
--- a/docs/supported-models.md
+++ b/docs/supported-models.md
@@ -40,7 +40,8 @@ deepseek-ai/DeepSeek-OCR deepseek-ai ocr ✔
deepseek-ai/DeepSeek-OCR-2 deepseek-ai ocr
Tencent-Hunyuan/HunyuanOCR Tencent-Hunyuan ocr ✔
PaddlePaddle/PaddleOCR-VL PaddlePaddle ocr ✔
-PaddlePaddle/PaddleOCR-VL-1.5 PaddlePaddle ocr
+PaddlePaddle/PaddleOCR-VL-1.5 PaddlePaddle ocr
+PaddlePaddle/PaddleOCR-VL-1.6 PaddlePaddle ocr ✔
AI-ModelScope/RMBG-2.0 AI-ModelScope image ✔
OpenBMB/VoxCPM-0.5B OpenBMB tts ✔
OpenBMB/VoxCPM1.5 OpenBMB tts ✔
@@ -88,7 +89,7 @@ ZhipuAI/GLM-OCR ZhipuAI ocr ✔
| Model | Languages | Model Id | License |
|-------|-----------|--------|---------|
-| **PaddleOCR-VL** | Multi | PaddlePaddle/PaddleOCR-VL
PaddlePaddle/PaddleOCR-VL-1.5 | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) |
+| **PaddleOCR-VL** | Multi | PaddlePaddle/PaddleOCR-VL
PaddlePaddle/PaddleOCR-VL-1.5
PaddlePaddle/PaddleOCR-VL-1.6 | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) |
| **Hunyuan-OCR** | Chinese | Tencent-Hunyuan/HunyuanOCR | [Tencent Hunyuan Community License](https://huggingface.co/tencent/HunyuanOCR/blob/main/LICENSE) |
| **DeepSeek-OCR** | Multi | deepseek-ai/DeepSeek-OCR
deepseek-ai/DeepSeek-OCR-2 | [MIT](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md) |
| **GLM-OCR** | 8 | ZhipuAI/GLM-OCR | [MIT](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md) |
diff --git a/docs/supported-models.zh-CN.md b/docs/supported-models.zh-CN.md
index 0395370..c86df15 100644
--- a/docs/supported-models.zh-CN.md
+++ b/docs/supported-models.zh-CN.md
@@ -40,7 +40,8 @@ deepseek-ai/DeepSeek-OCR deepseek-ai ocr ✔
deepseek-ai/DeepSeek-OCR-2 deepseek-ai ocr
Tencent-Hunyuan/HunyuanOCR Tencent-Hunyuan ocr ✔
PaddlePaddle/PaddleOCR-VL PaddlePaddle ocr ✔
-PaddlePaddle/PaddleOCR-VL-1.5 PaddlePaddle ocr
+PaddlePaddle/PaddleOCR-VL-1.5 PaddlePaddle ocr
+PaddlePaddle/PaddleOCR-VL-1.6 PaddlePaddle ocr ✔
AI-ModelScope/RMBG-2.0 AI-ModelScope image ✔
OpenBMB/VoxCPM-0.5B OpenBMB tts ✔
OpenBMB/VoxCPM1.5 OpenBMB tts ✔
@@ -86,7 +87,7 @@ ZhipuAI/GLM-OCR ZhipuAI ocr ✔
| 模型 | 语言 | 模型id | 开源协议 |
|------|------|------|---------|
-| **PaddleOCR-VL** | 多语言 | PaddlePaddle/PaddleOCR-VL
PaddlePaddle/PaddleOCR-VL-1.5 | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) |
+| **PaddleOCR-VL** | 多语言 | PaddlePaddle/PaddleOCR-VL
PaddlePaddle/PaddleOCR-VL-1.5
PaddlePaddle/PaddleOCR-VL-1.6 | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) |
| **Hunyuan-OCR** | 中文 | Tencent-Hunyuan/HunyuanOCR | [腾讯混元社区许可协议](https://huggingface.co/tencent/HunyuanOCR/blob/main/LICENSE) |
| **DeepSeek-OCR** | 多语言 | deepseek-ai/DeepSeek-OCR
deepseek-ai/DeepSeek-OCR-2 | [MIT](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md) |
| **GLM-OCR** | 8 | ZhipuAI/GLM-OCR | [MIT](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md) |
diff --git a/src/cli/mod.rs b/src/cli/mod.rs
index 82b43eb..fe3f8c8 100644
--- a/src/cli/mod.rs
+++ b/src/cli/mod.rs
@@ -298,9 +298,7 @@ pub(crate) fn run_run(args: RunArgs) -> anyhow::Result<()> {
WhichModel::HunyuanOCR => {
hunyuan_ocr::HunyuanORExec::run(&input, output.as_deref(), &weight_path)?;
}
- WhichModel::PaddleOCRVL
- | WhichModel::PaddleOCRVL1_5
- | WhichModel::PaddleOCRVL1_6 => {
+ WhichModel::PaddleOCRVL | WhichModel::PaddleOCRVL1_5 | WhichModel::PaddleOCRVL1_6 => {
paddleocr_vl::PaddleOVLExec::run(&input, output.as_deref(), &weight_path)?;
}
WhichModel::RMBG2_0 => {
diff --git a/src/models/mod.rs b/src/models/mod.rs
index 7a112af..19a6d0b 100644
--- a/src/models/mod.rs
+++ b/src/models/mod.rs
@@ -284,9 +284,7 @@ pub fn load_model<'a>(
let model = HunyuanOCRGenerateModel::init(path, device, dtype)?;
ModelInstance::HunyuanOCR(model)
}
- WhichModel::PaddleOCRVL
- | WhichModel::PaddleOCRVL1_5
- | WhichModel::PaddleOCRVL1_6 => {
+ WhichModel::PaddleOCRVL | WhichModel::PaddleOCRVL1_5 | WhichModel::PaddleOCRVL1_6 => {
let model = PaddleOCRVLGenerateModel::init(path, device, dtype)?;
ModelInstance::PaddleOCRVL(Box::new(model))
}