Hello๐ We are building a voice assistant AI and would value your inputs. We need to improve the trigger word detection accuracy of the model, please kindly take a minute to upload 2 voice clips of you saying the wake words "Hey Bizz Buddy" and "Hey Buddy" to this form:
Google released Gemma 4 12B, a multimodal model that runs text, images, and audio on 8GB VRAM!
We'll fine-tune it to master chess and predict the exact next move.
Tech stack:
- @UnslothAI for efficient fine-tuning.
- @huggingface transformers to run it locally.
Let's go! ๐