OmniVoice Latin (audio.cpp GGUF)

GGUF conversion of OmniVoice with the step-4000 Latin LoRA merged in (~22 h of macronized Latin).

LoRA card: coolcoder613/omnivoice-latin-lora-1.
Original GGUF card: coolcoder613/omnivoice-latin-GGUF-1.

  • omnivoice-latin-f32.gguf
  • omnivoice-latin-bf16.gguf
  • omnivoice-latin-q8_0.gguf
  • omnivoice-latin-q4_k.gguf
audiocpp_cli --task tts --family omnivoice --model omnivoice-latin-q8_0.gguf \
  --language Latin --text "Gallia est omnis dīvīsa in partēs trēs." --out out.wav
Downloads last month
287
GGUF
Hardware compatibility
Log In to add your hardware

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 coolcoder613/omnivoice-latin-GGUF-audio.cpp

Finetuned
Qwen/Qwen3-0.6B
Finetuned
k2-fsa/OmniVoice
Quantized
(47)
this model