toebee

Thank you! You can add audio prompts of calm voices to make them a bit smoother. https://huggingface.co/spaces/nari-labs/Dia-1.6B you can try it here!

Thank you!! Works for English only unfortunately :((

Thanks for the kind words! We're just following our interests and staying upwind.

Thanks for the kind words! You can try it now on https://huggingface.co/spaces/nari-labs/Dia-1.6B Also, we'll try to update the Demo Page to something lighter when we have time. Thanks for the feedback :))

Yes! But you would need to put together a LLM system that created scripts from the book content. There is an open source project called OpenNotebookLM (https://github.com/gabrielchua/open-notebooklm) that does something similar. If you hook the Dia model to that kind of system, it will be very possible :) Thanks for the interest!

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

We just clarified in the README, sorry for the confusion ;(

Note that the model was not fine-tuned on a specific voice. Hence, you will get different voices every time you run the model. You can keep speaker consistency by either adding an audio prompt (a guide coming VERY soon - try it with the second example on Gradio or HF Space for now), or fixing the seed.

Only two voices at the moment... We will need to upgrade the dataset to make that happen, and are considering that as one of the next steps.

https://huggingface.co/spaces/nari-labs/Dia-1.6B we fixed it!

You can try it now on https://huggingface.co/spaces/nari-labs/Dia-1.6B !!!

Thanks for the kind words :)))

We'll try to give a high-level overview when we publish the technical report!

Thank you for the kind words! We don't have plans for that yet, but you can always open an issue or RP on Github.

We have a ZeroGPU Space provided by HuggingFace up and running! Test it now on https://huggingface.co/spaces/nari-labs/Dia-1.6B

We're still experimenting, so do not have samples yet from the larger model. All we have is Dia-1.6B at the moment.

Thank you for the contribution! We'll be merging PRs and cleaning code up very soon :)

Sorry for the confusion. the license is plain Apache 2.0, and we changed the wording to "intended for research and educational use." The point was, users are free to use it for their use cases, just don't do shady stuff with it.

Thanks for the feedback :)

We are in the progress of fixing it! Thanks for letting us know :)

We use descript audio codec! I’m not sure if DAC works on iOS…

Thank you for the kind words! Dia wasn’t fine tuned on certain speaker, so you will get random voices every time you run it, unless you add a prompt / fix the seed.

The outputs are a bit unstable, might need to add cleaner training data and run longer training sessions. Hopefully we can do something like OAI Whisper and update with better performing checkpoints!

Thank you!! Indeed the script was inspired from a scene in the Office.

Thank you for the kind words <3

It is way past bedtime here, will be getting back to comments after a few hours of sleep! Thanks for all the kind words and feedback

You can add an audio prompt and prepend text corresponding to it in the script. You can get a feel for it by trying the second example in the Gradio interface!

Unfortunately yes at the moment

We will work on a quantized version of the model, so hopefully you will be able to run it soon!

We've seen Bark from Suno go from 16GB requirement -> 4GB requirement + running on CPUs. Won't be too hard, just need some time to work on it.

Sounds awesome! I think it won't be very hard to run it using output streaming, although that might require beefier GPUs. Give us an email and we can talk more - nari.ai.contact at gmail dot com.

It's way past bedtime where I live, so will be able to get back to you after a few hours. Thanks for the interest :)

We're envisioning a platform with a social aspect, so that is the biggest difference. Also, bigger models!

We are aware of the fact that you do not need to create a venv when using pre-existing uv. Just added it for people spinning up new GPUs on cloud. But I'll update the README to make that a bit clearer. Thanks for the feedback :)

Interesting. I haven't thought of that problem before. I'm guessing a large enough audio dataset for medical terminology does not exist publicly.

But AFAIK, even if you have just a few hours of audio containing specific terminology (and correct pronunciation), fine-tuning on that data will significantly improve performance.

Thanks for the heads-up! We weren’t aware of the GNOME Dia project. Since we focus on speech AI, we’ll make sure to clarify that distinction.