Is this 100% natural speech or partly synthetic too? Because sample 2/16 on the website doesn't sound natural at all, but maybe it's just an outlier
Francesco Cariaggi
anferico
AI & ML interests
Natural Language Processing, Computer Vision, Edge Computing
Recent Activity
commentedon an article about 1 month ago
Open Yap 1K: 1,000 hours of full-duplex natural conversation, free for commercial use liked a dataset 6 months ago
wikimedia/structured-wikipedia upvoted an article 6 months ago
⚡ nano-vLLM: Lightweight, Low-Latency LLM Inference from ScratchOrganizations
commented on Open Yap 1K: 1,000 hours of full-duplex natural conversation, free for commercial use about 1 month ago
liked a
dataset 6 months ago
upvoted an article 6 months ago
Article
⚡ nano-vLLM: Lightweight, Low-Latency LLM Inference from Scratch
zamal
• • 49 liked 3
datasets 6 months ago
Would you release the pre-trained AuT model?
👍 13
3
#10 opened about 1 year ago
by 
JosephusCheung
TTS tokenizer for Qwen3-Omni
1
#3 opened 8 months ago
by anferico
liked 4
models 8 months ago
updated 4
models about 1 year ago
updated a
collection over 1 year ago