search

ggerganov / whisper.cpp

Port of OpenAI's Whisper model in C/C++
MIT License
35.73k stars 3.64k forks source link

talk-llama segmentation fault on mac os #691

Open starsea opened 1 year ago

starsea commented 1 year ago

there is no file named ggml-model-q4_0.bin

llama_model_load: loading model from './models/7B/ggml-model-q4_0.bin' - please wait ... llama_model_load: failed to open './models/7B/ggml-model-q4_0.bin' llama_init_from_file: failed to load model

main: processing, 8 threads, lang = en, task = transcribe, timestamps = 0 ...

init: found 2 capture devices: init: - Capture device #0: 'BlackHole 2ch' init: - Capture device #1: 'MacBook Air麦克风' init: attempt to open capture device 1 : 'MacBook Air麦克风' ... init: obtained spec for input device (SDL Id = 2): init: - sample rate: 16000 init: - format: 33056 (required: 33056) init: - channels: 1 (required: 1) init: - samples per frame: 1024 [1] 79724 segmentation fault ./talk-llama -mw ./models/ggml-base.en.bin -ml -p "Georgi" -t 8 -c 1

prusnak commented 1 year ago

Follow the instructions in https://github.com/ggerganov/llama.cpp to generate the ./models/7B/ggml-model-q4_0.bin/ggml-model-q4_0.bin file.