gguf quantized version of higgs

  • base model from bosonai
  • text-to-speech synthesis

run it with gguf-connector

ggc h2

screenshot

Prompt Audio Sample
[SPEAKER0] Hey Connector, why your appearance looks so stupid?
[SPEAKER1] Oh, really? maybe I ate too much smart beans.
[SPEAKER0] Wow. Awesome!
[SPEAKER1] Do you want some?
🎧 audio-1-english

안녕히 주무셨어요?
🎧 audio-2-korean

你好
🎧 audio-3-chinese

Herzlichen Glückwunsch
🎧 audio-4-german

Que tenga usted buenos días
🎧 audio-5-spanish

こんにちは
🎧 audio-6-japanese

reference

  • simply execute the command (ggc h2) above in console/terminal
  • note: model file(s) will be pulled to local cache automatically during the first launch; then opt to run it entirely offline; i.e., from local URL: http://127.0.0.1:7860 with lazy webui
  • gguf-connector (pypi)
Downloads last month
462
GGUF
Model size
5.77B params
Architecture
pig
Hardware compatibility
Log In to view the estimation

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

32-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for calcuis/higgs-gguf

Quantized
(1)
this model