FireRed-OCR
FireRed-OCR is a framework that specializes large vision-language models into pixel-precise structural document parsing models.
- Type
- Multimodal
- Weights
- Open
- Downloads
- 938
- Likes
- 167
- Pipeline
- image to text
- License
- apache-2.0
Model hub
FireRedTeam/FireRed-OCR
- Repo
- FireRedTeam/FireRed-OCR
- Access
- Public
Technical tags and languages
Papers
1
More from FireRedTeam
6
-
41k DL
FireRed Image Edit
Image
FireRed-Image-Edit is a general-purpose image editing model aimed at high-fidelity, consistent instruction-ba…
-
FireRed OpenStoryline
Video
FireRed-OpenStoryline is an AI video editing agent that turns natural-language intent into an editing workflo…
-
FireRedASR2S
Audio
FireRedASR2S is an industrial-grade all-in-one ASR system combining ASR, VAD, LID, and punctuation modules.
-
FireRedChat
Multimodal
FireRedChat is a fully self-hosted system for building real-time, full-duplex voice AI agents.
-
FireRedTTS 2
Audio
FireRedTTS-2 is a long-form streaming TTS system for multi-speaker dialogue generation.