dia-gguf

calcuis/dia-gguf

dia-gguf is a text-to-speech model from calcuis. Use it when you need text read aloud. The card lists the license as apache-2.0.

- run it with gguf-connector; simply execute the command below in console/terminal

Downloads · 30 days

523

11% of all-time downloads

All-time downloads

4.7K

Public

Repo size

48.5 GB

Likes

Public

Repo makeup

Click a slice to open those files.

.gguf34.2 GB · 100%

From the Hugging Face model README

run it with gguf-connector; simply execute the command below in console/terminal

ggc s6

GGUF file(s) available. Select which one to use:

dia-1.6b-iq3_xxs.gguf

dia-1.6b-iq4_nl.gguf

dia-1.6b-iq4_xs.gguf

Enter your choice (1 to 3): _

screenshot

Prompt	Audio Sample
`[S1] This is an open weights text to dialogue model.`<br/>`[S2] You get full control over scripts and voices.`<br/>`[S1] Wow. Amazing. (laughs)`<br/>`[S2] Try it now on Git hub or Hugging Face.`<br/>	🎧 dia-sample-1<br><audio controls src="https://huggingface.co/calcuis/dia-gguf/resolve/main/samples%5Caudio1.wav"></audio>
`[S1] Hey Connector, why your appearance looks so stupid?`<br/>`[S2] Oh, really? maybe I ate too much smart beans.`<br/>`[S1] Wow. Amazing. (laughs)`<br/>`[S2] Let's go to get some more smart beans and you will become stupid as well.`<br/>	🎧 dia-sample-2<br><audio controls src="https://huggingface.co/calcuis/dia-gguf/resolve/main/samples%5Caudio2.wav"></audio>

ggc s2

note: differ from ggc s6, for ggc s2, model file(s) will be pulled to local cache automatically during the first launch (if you don't have gguf in your current directory, it will shift to s2 mode); then opt to run it entirely offline; i.e., from local URL: http://127.0.0.1:7860 with lazy webui