(github.com)

652 points toebee | 3 comments | 21 Apr 25 17:07 UTC | HN request time: 0.457s | source

1. youssefabdelm ◴[21 Apr 25 19:00 UTC] No.43755275[source]▶

Anyone know if possible to fine-tune for cloning my voice?

2. toebee ◴[22 Apr 25 00:53 UTC] No.43758100[source]▶

We're adding guides for Zero-shot voice cloning. You can try it using the second example on Gradio: https://huggingface.co/spaces/nari-labs/Dia-1.6B

replies(1): >>43762131 #

3. youssefabdelm ◴[22 Apr 25 13:46 UTC] No.43762131[source]▶

Will give it a shot but I feel like fine-tuning will be more reliable, any way to do that?

Show HN: Dia, an open-weights TTS model for generating realistic dialogue