Transformers v5.21.0新增OCR、MoE、视觉与TTS模型
Transformers v5.21.0新增对OpenBMB文档理解模型MiniCPM-OCR、Recursive混合专家语言模型Flint、用于视觉文档理解与检索的UltraVBert、Gradium Phonon TTS和Kyutai Pocket TTS的支持。发布说明称，MiniCPM-OCR专用于处理扫描页、截图、收据和表格等文字密集图像。量化方面的改动修复了DeepSeek-V4.1的FP4专家处理，并避免TimesFM 2.5在使用4位或8位量化加载时将浮点输入转换为整数权重数据类型。此次发布还包含错误修复和基础设施更新。
此次发布将文档理解、语言、视觉检索和语音领域的更多模型纳入Transformers，并调整了对DeepSeek-V4.1和TimesFM 2.5的量化支持。
Release v5.21.0
New Model additions
MiniCPM-OCR
MiniCPM-OCR is a document-understanding model from OpenBMB's MiniCPM-V family. It keeps the MiniCPM-V 4.6 architecture, which pairs a SigLIP vision encoder and a window-attention merger with a Qwen3.5 language model. It is specialized for reading text-dense images such as scanned pages, screenshots, receipts and tables.
Links: Documentation | Paper
#Transformers#MiniCPM-OCR#OpenBMB#Flint#Recursive#UltraVBERT#Gradium Phonon TTS#Pocket TTS#Kyutai#DeepSeek-V4.1#TimesFM 2.5