mirror of
https://github.com/ggerganov/whisper.cpp.git
synced 2025-01-29 15:44:06 +00:00
b0502836b8
* whisper : migrate to ggml-backend * whisper : fix logit reading * whisper : fix tensor allocation during load * whisper : fix beam-search with CUDA * whisper : free backends + fix compile warning * whisper : print when CUDA is enabled * whisper : fix CoreML * make : clean-up * talk : fix compile warning * whisper : support ggml_conv with CUDA and Metal (#1473) * ggml : add CUDA support for ggml_conv * whisper : remove ggml_repeat for conv bias + single backend * cuda : fix im2col kernel * metal : add im2col support + mul mat-vec f16 x f16 * bench-all : add q4 models * whisper : clean-up * quantize-all : fix * ggml : im2col opts * whisper : avoid whisper_model_data wrapper * whisper : add note that ggml_mul_mat_pad does not work with CUDA * whisper : factor out graph compute in common function * whisper : fixes * whisper : fix UB with measure buffers * whisper : try to fix the parallel whisper_state functionality (#1479) * whisper : try to fix the parallel whisper_state functionality * whisper : fix multi-state Metal * whisper : free backend instances in whisper_state
talk
Talk with an Artificial Intelligence in your terminal
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/resolve/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 script to your needs.
By default, it is configured to use MacOS's say or espeak or Windows SpeechSynthesizer, but you can use whatever you wish.