Category: Transformer

In this article, we fine-tune the Gemma 4 E2B model for audio transcription and translation. We train the model using Unsloth on a German transcription dataset. ...

In this article, we introduce Open Transcribe - an open-source real-time transcription application that runs on top of RealtimeSTT. ...

In this article, we create a real-time audio transcription application on of the RealtimeSTT library. ...

In this article, we are fine-tuning the Qwen3-VL 2B model for sketch and image to HTML. After fine-tuning, we will be able to feed an image of a website to the model and get the HTML code for it. ...

In this article we are fine-tuning the Phi-3.5 Vision Instruct model on a receipt OCR dataset. We are using Hugging Face libraries and training a LoRA. ...