Hey Thanks

[StuartIanNaylor]

Georgi, super clean well documented brilliant implementation.

Many Thanks

PS only thing with the streaming example on a rk3588

./main -m models/ggml-base.en.bin -f samples/jfk.wav -t 8
whisper_model_load: loading model from 'models/ggml-base.en.bin'
whisper_model_load: n_vocab       = 51864
whisper_model_load: n_audio_ctx   = 1500
whisper_model_load: n_audio_state = 512
whisper_model_load: n_audio_head  = 8
whisper_model_load: n_audio_layer = 6
whisper_model_load: n_text_ctx    = 448
whisper_model_load: n_text_state  = 512
whisper_model_load: n_text_head   = 8
whisper_model_load: n_text_layer  = 6
whisper_model_load: n_mels        = 80
whisper_model_load: f16           = 1
whisper_model_load: type          = 2
whisper_model_load: mem_required  = 505.00 MB
whisper_model_load: adding 1607 extra tokens
whisper_model_load: ggml ctx size = 163.43 MB
whisper_model_load: memory size =    22.83 MB
whisper_model_load: model size  =   140.54 MB

main: processing 'samples/jfk.wav' (176000 samples, 11.0 sec), 8 threads, lang = en, task = transcribe, timestamps = 1 ...


[00:00:00.000 --> 00:00:11.000]   And so my fellow Americans, ask not what your country can do for you, ask what you can do for your country.


whisper_print_timings:     load time =   375.09 ms
whisper_print_timings:      mel time =   106.11 ms
whisper_print_timings:   sample time =     0.00 ms
whisper_print_timings:   encode time =  6155.65 ms / 1025.94 ms per layer
whisper_print_timings:   decode time =   608.97 ms / 101.50 ms per layer
whisper_print_timings:    total time =  7258.99 ms

Posted that so you get an idea of perf, but when streaming its WARNING: cannot process audio fast enough, dropping audio ... and strangely thinks I am blowing kisses :) (blows kiss) - Me? (blows kiss)