arkobel·4 か月前·議論The lack of parallel accent data makes this fundamentally unsupervised. Curious if this leans more on latent disentanglement than direct supervision.
arkobel·6 か月前·議論Have you compared with Krisp-TT models? https://krisp.ai/blog/krisp-turn-taking-v2-voice-ai-viva-sdk... Krisp LLC also shares an End-of-Turn Test dataset. Did you test your model on that? https://huggingface.co/datasets/Krisp-AI/turn-taking-test-v1And can you share some information about the model size and FLOPS?