Created
February 7, 2024 09:08
-
-
Save fanweixiao/8a456a0cd56b37f514b5b11d64b5d6fe to your computer and use it in GitHub Desktop.
AWS Graviton3 32vCPUs
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
$ ./main -m models/ggml-base-q5_1.bin -f ~/zh.wav | |
whisper_init_from_file_with_params_no_state: loading model from 'models/ggml-base-q5_1.bin' | |
whisper_model_load: loading model | |
whisper_model_load: n_vocab = 51865 | |
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: ftype = 9 | |
whisper_model_load: qntvr = 1 | |
whisper_model_load: type = 2 (base) | |
whisper_model_load: adding 1608 extra tokens | |
whisper_model_load: n_langs = 99 | |
whisper_model_load: CPU total size = 59.22 MB (1 buffers) | |
whisper_model_load: model size = 59.12 MB | |
whisper_init_state: kv self size = 16.52 MB | |
whisper_init_state: kv cross size = 18.43 MB | |
whisper_init_state: compute buffer (conv) = 16.17 MB | |
whisper_init_state: compute buffer (encode) = 94.42 MB | |
whisper_init_state: compute buffer (cross) = 5.08 MB | |
whisper_init_state: compute buffer (decode) = 105.96 MB | |
system_info: n_threads = 4 / 32 | AVX = 0 | AVX2 = 0 | AVX512 = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | METAL = 0 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 | CUDA = 0 | COREML = 0 | OPENVINO = 0 | | |
main: processing '/home/ubuntu/zh.wav' (79949 samples, 5.0 sec), 4 threads, 1 processors, 5 beams + best of 5, lang = en, task = transcribe, timestamps = 1 ... | |
[00:00:00.000 --> 00:00:04.480] I think running is the most important thing for me to see health. | |
whisper_print_timings: load time = 53.78 ms | |
whisper_print_timings: fallbacks = 0 p / 0 h | |
whisper_print_timings: mel time = 6.41 ms | |
whisper_print_timings: sample time = 27.94 ms / 82 runs ( 0.34 ms per run) | |
whisper_print_timings: encode time = 1310.36 ms / 1 runs ( 1310.36 ms per run) | |
whisper_print_timings: decode time = 4.54 ms / 2 runs ( 2.27 ms per run) | |
whisper_print_timings: batchd time = 132.78 ms / 78 runs ( 1.70 ms per run) | |
whisper_print_timings: prompt time = 0.00 ms / 1 runs ( 0.00 ms per run) | |
whisper_print_timings: total time = 1539.46 ms |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
./main -m models/ggml-large-v3-q5_0.bin -f ~/zh.wav | |
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 = 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 = 8 | |
whisper_model_load: qntvr = 2 | |
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 = 1080.97 MB (2 buffers) | |
whisper_model_load: model size = 1080.47 MB | |
whisper_init_state: kv self size = 220.20 MB | |
whisper_init_state: kv cross size = 245.76 MB | |
whisper_init_state: compute buffer (conv) = 35.50 MB | |
whisper_init_state: compute buffer (encode) = 233.50 MB | |
whisper_init_state: compute buffer (cross) = 10.15 MB | |
whisper_init_state: compute buffer (decode) = 108.99 MB | |
system_info: n_threads = 4 / 32 | AVX = 0 | AVX2 = 0 | AVX512 = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | METAL = 0 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 | CUDA = 0 | COREML = 0 | OPENVINO = 0 | | |
main: processing '/home/ubuntu/zh.wav' (79949 samples, 5.0 sec), 4 threads, 1 processors, 5 beams + best of 5, lang = en, task = transcribe, timestamps = 1 ... | |
[00:00:00.000 --> 00:00:05.000] I think running is most important because it brings me health. | |
whisper_print_timings: load time = 326.38 ms | |
whisper_print_timings: fallbacks = 0 p / 0 h | |
whisper_print_timings: mel time = 7.40 ms | |
whisper_print_timings: sample time = 24.98 ms / 72 runs ( 0.35 ms per run) | |
whisper_print_timings: encode time = 29965.32 ms / 1 runs (29965.32 ms per run) | |
whisper_print_timings: decode time = 27.04 ms / 1 runs ( 27.04 ms per run) | |
whisper_print_timings: batchd time = 1586.20 ms / 69 runs ( 22.99 ms per run) | |
whisper_print_timings: prompt time = 0.00 ms / 1 runs ( 0.00 ms per run) | |
whisper_print_timings: total time = 31941.65 ms |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
./main -m models/ggml-medium-q5_0.bin -f ~/zh.wav | |
whisper_init_from_file_with_params_no_state: loading model from 'models/ggml-medium-q5_0.bin' | |
whisper_model_load: loading model | |
whisper_model_load: n_vocab = 51865 | |
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 1608 extra tokens | |
whisper_model_load: n_langs = 99 | |
whisper_model_load: CPU total size = 538.97 MB (1 buffers) | |
whisper_model_load: model size = 538.59 MB | |
whisper_init_state: kv self size = 132.12 MB | |
whisper_init_state: kv cross size = 147.46 MB | |
whisper_init_state: compute buffer (conv) = 28.00 MB | |
whisper_init_state: compute buffer (encode) = 187.14 MB | |
whisper_init_state: compute buffer (cross) = 8.46 MB | |
whisper_init_state: compute buffer (decode) = 107.98 MB | |
system_info: n_threads = 4 / 32 | AVX = 0 | AVX2 = 0 | AVX512 = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | METAL = 0 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 | CUDA = 0 | COREML = 0 | OPENVINO = 0 | | |
main: processing '/home/ubuntu/zh.wav' (79949 samples, 5.0 sec), 4 threads, 1 processors, 5 beams + best of 5, lang = en, task = transcribe, timestamps = 1 ... | |
[00:00:00.000 --> 00:00:04.400] I think the most important thing in running is to bring health to me. | |
whisper_print_timings: load time = 184.65 ms | |
whisper_print_timings: fallbacks = 0 p / 0 h | |
whisper_print_timings: mel time = 6.42 ms | |
whisper_print_timings: sample time = 19.27 ms / 71 runs ( 0.27 ms per run) | |
whisper_print_timings: encode time = 15536.68 ms / 1 runs (15536.68 ms per run) | |
whisper_print_timings: decode time = 14.88 ms / 1 runs ( 14.88 ms per run) | |
whisper_print_timings: batchd time = 847.85 ms / 68 runs ( 12.47 ms per run) | |
whisper_print_timings: prompt time = 0.00 ms / 1 runs ( 0.00 ms per run) | |
whisper_print_timings: total time = 16613.97 ms |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
$ ./main -m models/ggml-small-q5_1.bin -f ~/zh.wav | |
whisper_init_from_file_with_params_no_state: loading model from 'models/ggml-small-q5_1.bin' | |
whisper_model_load: loading model | |
whisper_model_load: n_vocab = 51865 | |
whisper_model_load: n_audio_ctx = 1500 | |
whisper_model_load: n_audio_state = 768 | |
whisper_model_load: n_audio_head = 12 | |
whisper_model_load: n_audio_layer = 12 | |
whisper_model_load: n_text_ctx = 448 | |
whisper_model_load: n_text_state = 768 | |
whisper_model_load: n_text_head = 12 | |
whisper_model_load: n_text_layer = 12 | |
whisper_model_load: n_mels = 80 | |
whisper_model_load: ftype = 9 | |
whisper_model_load: qntvr = 1 | |
whisper_model_load: type = 3 (small) | |
whisper_model_load: adding 1608 extra tokens | |
whisper_model_load: n_langs = 99 | |
whisper_model_load: CPU total size = 189.68 MB (1 buffers) | |
whisper_model_load: model size = 189.49 MB | |
whisper_init_state: kv self size = 49.55 MB | |
whisper_init_state: kv cross size = 55.30 MB | |
whisper_init_state: compute buffer (conv) = 22.08 MB | |
whisper_init_state: compute buffer (encode) = 140.78 MB | |
whisper_init_state: compute buffer (cross) = 6.77 MB | |
whisper_init_state: compute buffer (decode) = 106.97 MB | |
system_info: n_threads = 4 / 32 | AVX = 0 | AVX2 = 0 | AVX512 = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | METAL = 0 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 | CUDA = 0 | COREML = 0 | OPENVINO = 0 | | |
main: processing '/home/ubuntu/zh.wav' (79949 samples, 5.0 sec), 4 threads, 1 processors, 5 beams + best of 5, lang = en, task = transcribe, timestamps = 1 ... | |
[00:00:00.000 --> 00:00:04.360] I think the most important thing to do is to bring me a healthy body. | |
whisper_print_timings: load time = 86.54 ms | |
whisper_print_timings: fallbacks = 0 p / 0 h | |
whisper_print_timings: mel time = 6.43 ms | |
whisper_print_timings: sample time = 29.51 ms / 87 runs ( 0.34 ms per run) | |
whisper_print_timings: encode time = 4970.38 ms / 1 runs ( 4970.38 ms per run) | |
whisper_print_timings: decode time = 0.00 ms / 1 runs ( 0.00 ms per run) | |
whisper_print_timings: batchd time = 398.29 ms / 85 runs ( 4.69 ms per run) | |
whisper_print_timings: prompt time = 0.00 ms / 1 runs ( 0.00 ms per run) | |
whisper_print_timings: total time = 5495.13 ms |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment