Interact with this model by speaking to it. Lean, fast, & private, networked speech to text, AI images, multi-modal voice chat, control apps, webcam, and sound with less than 4GiB of VRAM.
bash
1git clone -b main --single-branch https://github.com/themanyone/whisper_dictation.git
2pip install -r whisper_dictation/requirements.txt
34git clone https://github.com/ggerganov/whisper.cpp
5cd whisper.cpp
6GGML_CUDA=1make -j # assuming CUDA is available. see docs7ln -s server ~/.local/bin/whisper_cpp_server # (just put it somewhere in $PATH)89# -ngl option assums AI accelerator like CUDA is available10llama-server --hf-repo hellork/law-chat-IQ4_NL-GGUF --hf-file law-chat-iq4_nl-imat.gguf -c 2048 -ngl 17 --port 888811whisper_cpp_server -l en -m models/ggml-tiny.en.bin --port 777712cd whisper_dictation
13./whisper_cpp_client.py
See the docs for tips on integrating with llama.cpp server, enabling the computer to talk back, draw AI images, carry out voice commands, and other features.
Install Llama.cpp via git:
Step 1: Clone llama.cpp from GitHub.
git clone https://github.com/ggerganov/llama.cpp
Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
cd llama.cpp && LLAMA_CURL=1 make
Step 3: Run inference through the main binary.
./llama-cli --hf-repo hellork/law-chat-IQ4_NL-GGUF --hf-file law-chat-iq4_nl-imat.gguf -p "The meaning to life and the universe is"
