whisper-cpp_output

E:\___trash\whisper-cpp>main.exe -m ggml-large-v3.bin -f audio-20240220-0001_garbage.wav -otxt -ovtt -osrt
whisper_init_from_file_with_params_no_state: loading model from 'ggml-large-v3.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 = 51866
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 1280
whisper_model_load: n_audio_head = 20
whisper_model_load: n_audio_layer = 32
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 1280
whisper_model_load: n_text_head = 20
whisper_model_load: n_text_layer = 32
whisper_model_load: n_mels = 128
whisper_model_load: ftype = 1
whisper_model_load: qntvr = 0
whisper_model_load: type = 5 (large v3)
whisper_model_load: adding 1609 extra tokens
whisper_model_load: n_langs = 100
whisper_model_load: CPU total size = 3094.36 MB
whisper_model_load: model size = 3094.36 MB
whisper_init_state: kv self size = 251.66 MB
whisper_init_state: kv cross size = 251.66 MB
whisper_init_state: kv pad size = 7.86 MB
whisper_init_state: compute buffer (conv) = 36.26 MB
whisper_init_state: compute buffer (encode) = 926.66 MB
whisper_init_state: compute buffer (cross) = 9.38 MB
whisper_init_state: compute buffer (decode) = 213.19 MB

system_info: n_threads = 4 / 12 | 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 'audio-20240220-0001_garbage.wav' (810655 samples, 50.7 sec), 4 threads, 1 processors, 5 beams + best of 5, lang = en, task = transcribe, timestamps = 1 ...

 

[00:00:00.320 --> 00:00:01.160] - Story time.
[00:00:01.160 --> 00:00:04.400] Just had an amazing night with some friends.
[00:00:04.400 --> 00:00:06.080] And it was very funny, while we were waiting for our Uber,
[00:00:06.080 --> 00:00:09.800] we just got like interrogated by a drunk man
[00:00:09.800 --> 00:00:10.920] who was kind of chill.
[00:00:10.920 --> 00:00:13.400] But also like if you met extended family
[00:00:13.400 --> 00:00:15.080] who just wanted to know all the details of your life
[00:00:15.080 --> 00:00:19.720] in a very like college, marriage, job sort of way.
[00:00:19.720 --> 00:00:21.120] And I was like, really random.
[00:00:21.120 --> 00:00:23.480] Then we got an Uber and then we were driving,
[00:00:23.480 --> 00:00:25.960] a car almost crashed into us
[00:00:25.960 --> 00:00:27.480] and then they crashed into the center divider
[00:00:27.480 --> 00:00:29.020] and then proceeded just to follow us
[00:00:29.020 --> 00:00:31.780] like five feet away from us with two blown tires.
[00:00:31.780 --> 00:00:34.580] - And then passed us.
[00:00:34.580 --> 00:00:36.640] - And then passed us.
[00:00:36.640 --> 00:00:38.060] - And a few other cars.
[00:00:38.060 --> 00:00:39.960] - And a few other cars.
[00:00:39.960 --> 00:00:41.480] And our Uber driver was really chill,
[00:00:41.480 --> 00:00:44.100] kept a really level head but like,
[00:00:44.100 --> 00:00:45.720] wouldn't end to a night.
[00:00:45.720 --> 00:00:48.320] We're safe in the hotel now, obviously nothing happened,
[00:00:48.320 --> 00:00:49.160] but like.
[00:00:49.160 --> 00:00:51.160] *Gasp*

output_txt: saving output to 'audio-20240220-0001_garbage.wav.txt'
output_vtt: saving output to 'audio-20240220-0001_garbage.wav.vtt'
output_srt: saving output to 'audio-20240220-0001_garbage.wav.srt'

whisper_print_timings: load time = 2123.37 ms
whisper_print_timings: fallbacks = 1 p / 0 h
whisper_print_timings: mel time = 40.85 ms
whisper_print_timings: sample time = 838.41 ms / 1257 runs ( 0.67 ms per run)
whisper_print_timings: encode time = 106996.87 ms / 3 runs (35665.62 ms per run)
whisper_print_timings: decode time = 0.00 ms / 1 runs ( 0.00 ms per run)
whisper_print_timings: batchd time = 41016.61 ms / 1246 runs ( 32.92 ms per run)
whisper_print_timings: prompt time = 3919.58 ms / 147 runs ( 26.66 ms per run)
whisper_print_timings: total time = 155017.19 ms