Instructions to use Serveurperso/OmniVoice-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Serveurperso/OmniVoice-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Serveurperso/OmniVoice-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf Serveurperso/OmniVoice-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Serveurperso/OmniVoice-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf Serveurperso/OmniVoice-GGUF:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf Serveurperso/OmniVoice-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Serveurperso/OmniVoice-GGUF:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf Serveurperso/OmniVoice-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Serveurperso/OmniVoice-GGUF:Q4_K_M
Use Docker
docker model run hf.co/Serveurperso/OmniVoice-GGUF:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use Serveurperso/OmniVoice-GGUF with Ollama:
ollama run hf.co/Serveurperso/OmniVoice-GGUF:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use Serveurperso/OmniVoice-GGUF with Docker Model Runner:
docker model run hf.co/Serveurperso/OmniVoice-GGUF:Q4_K_M
- Lemonade
How to use Serveurperso/OmniVoice-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Serveurperso/OmniVoice-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.OmniVoice-GGUF-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Really surprised
#2
by Camekanss - opened
Using it with RX 590 and it takes like 25-30 seconds to generate a 12 seconds of audio clip so it`s really fast given that my GPU is old as hell. Was using pocket tts but this really surprised me because it can even handle Turkish, Spanish and Russian very good. Using the Q8 btw
Camekanss changed discussion status to closed
Camekanss changed discussion status to open
Agree, Q8 works really fast on my 1050 Ti as well. Was totally worth the headache of compiling