Transformers v5.21.0 Adds OCR, MoE, Vision and TTS Models
Transformers v5.21.0 adds support for OpenBMB’s MiniCPM-OCR document-understanding model, Recursive’s Flint mixture-of-experts language model, UltraVBert for visual document understanding and retrieval, Gradium Phonon TTS and Kyutai’s Pocket TTS. The release notes describe MiniCPM-OCR as specialized for text-dense images such as scanned pages, screenshots, receipts and tables. Quantization changes address DeepSeek-V4.1’s FP4 experts and prevent TimesFM 2.5 from casting float inputs to integer weight dtypes when loaded with 4-bit or 8-bit quantization. The release also includes bug fixes and infrastructure updates.
The release expands the model families available in Transformers across document understanding, language, visual retrieval and speech, while also changing quantization support for DeepSeek-V4.1 and TimesFM 2.5.
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