半颗白菜
半颗白菜
``` $./main -m models/ggml-large-v3-q5_0.bin -f output.wav -l auto whisper_init_from_file_with_params_no_state: loading model from 'models/ggml-large-v3-q5_0.bin' whisper_model_load: loading model whisper_model_load: n_vocab = 51866 whisper_model_load: n_audio_ctx = 1500 whisper_model_load: n_audio_state = 1280 whisper_model_load: n_audio_head...
By adding this workflow, the Docker image it builds becomes more lightweight.  You can see that the built image is one-tenth the size of the original image.
``` 2024-04-23T11:14:05.440428411Z │ │ o = [ │ │ 2024-04-23T11:14:05.440433580Z │ │ │ { │ │ 2024-04-23T11:14:05.440438329Z │ │ │ │ 'filename': │ │ 2024-04-23T11:14:05.440444615Z │ │ 'ca57298e615ab2d4875db18590befaad.png', │ │...
Hello