# Synthetic data augmentation

This model is a dialogue turn detection model fine-tuned based on Qwen3-0.6B. It uses the Unsloth and Huggingface TRL libraries to accelerate training, achieving an accuracy of 96.22% in the dialogue turn detection task.

SauerkrautTTS-Preview-0.1 is a German text-to-speech (TTS) model fine-tuned from a powerful base model, offering four unique German speaker voices.

AeroGen is the first model that supports both horizontal and rotated bounding box conditional generation, capable of generating high-quality synthetic images that meet specific layout and object category requirements.

This is a fine-tuned version of Dicta - IL's dictalm2.0 - instruct model, specifically designed for generating Hebrew question-answer pairs.

Depth Anything V2 is a depth estimation model based on the DPT architecture, utilizing a DINOv2 backbone network. It achieves fine and robust depth prediction through training on large-scale synthetic and real-world data.

Bengali speech recognition model based on wav2vec2-xls-r-300m architecture, fine-tuned for specific command sets