running example use too long time in linux

[li-henan]

Dear author,
thanks for your code, I make and run ./main -m ggml-model-whisper-base.en.bin -f samples/jfk.wav -bs 1
but the process use about an hour, and the result is as follows,
it is there any problem in installing ? Or my linux environment is wrong ?
I will appreciate if you can help, thanks!

-> % ./main -m ggml-model-whisper-medium.en-q5_0.bin -f samples/jfk.wav -bs 1
whisper_init_from_file_with_params_no_state: loading model from 'ggml-model-whisper-medium.en-q5_0.bin'
whisper_init_with_params_no_state: use gpu = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
whisper_model_load: loading model
whisper_model_load: n_vocab = 51864
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 1024
whisper_model_load: n_audio_head = 16
whisper_model_load: n_audio_layer = 24
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 1024
whisper_model_load: n_text_head = 16
whisper_model_load: n_text_layer = 24
whisper_model_load: n_mels = 80
whisper_model_load: ftype = 8
whisper_model_load: qntvr = 1
whisper_model_load: type = 4 (medium)
whisper_model_load: adding 1607 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: CPU total size = 538.59 MB
whisper_model_load: model size = 538.59 MB
whisper_mel_init: n_len = 6000, n_len_org = 6000, n_mel = 80
whisper_init_state: kv self size = 150.99 MB
whisper_init_state: kv cross size = 150.99 MB
whisper_init_state: kv pad size = 6.29 MB
whisper_init_state: compute buffer (conv) = 28.68 MB
whisper_init_state: compute buffer (encode) = 594.22 MB
whisper_init_state: compute buffer (cross) = 7.85 MB
whisper_init_state: compute buffer (decode) = 142.09 MB

system_info: n_threads = 4 / 8 | AVX = 1 | AVX2 = 1 | AVX512 = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | METAL = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | CUDA = 0 | COREML = 0 | OPENVINO = 0

main: processing 'samples/jfk.wav' (176000 samples, 11.0 sec), 4 threads, 1 processors, 1 beams + best of 5, lang = en, task = transcribe, timestamps = 1 ...

whisper_mel_init: n_len = 4100, n_len_org = 1099, n_mel = 80

[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 = 2482.54 ms
whisper_print_timings: fallbacks = 0 p / 0 h
whisper_print_timings: mel time = 182.05 ms
whisper_print_timings: sample time = 41.48 ms / 1 runs ( 41.48 ms per run)
whisper_print_timings: encode time = 233645.86 ms / 1 runs (233645.86 ms per run)
whisper_print_timings: decode time = 2577285.00 ms / 27 runs (95455.00 ms per run)
whisper_print_timings: batchd time = 0.00 ms / 1 runs ( 0.00 ms per run)
whisper_print_timings: prompt time = 0.00 ms / 1 runs ( 0.00 ms per run)
whisper_print_timings: total time = 2814680.00 ms

[tannisroot]

I have the same issue but with the SYCL backend