Georgi Gerganov 5fd1bdd7fc
whisper : add GPU support via cuBLAS (#834)
* make : add WHISPER_CUBLAS

* make : fix CUBLAS build

* whisper : disable Flash Attention + adjust memory buffers

* whisper : remove old commented code

* readme : add cuBLAS instructions

* cmake : add WHISPER_CUBLAS option

* gitignore : ignore build-cublas
2023-04-30 12:14:33 +03:00
..
2022-12-10 16:51:58 +02:00

talk

Talk with an Artificial Intelligence in your terminal

Demo Talk

Web version: examples/talk.wasm

Building

The talk tool depends on SDL2 library to capture audio from the microphone. You can build it like this:

# Install SDL2 on Linux
sudo apt-get install libsdl2-dev

# Install SDL2 on Mac OS
brew install sdl2

# Build the "talk" executable
make talk

# Run it
./talk -p Santa

GPT-2

To run this, you will need a ggml GPT-2 model: instructions

Alternatively, you can simply download the smallest ggml GPT-2 117M model (240 MB) like this:

wget --quiet --show-progress -O models/ggml-gpt-2-117M.bin https://huggingface.co/ggerganov/ggml/raw/main/ggml-model-gpt-2-117M.bin

TTS

For best experience, this example needs a TTS tool to convert the generated text responses to voice. You can use any TTS engine that you would like - simply edit the speak.sh script to your needs. By default, it is configured to use espeak, but you can use whatever you wish.