mirror of https://github.com/ggerganov/whisper.cpp.git synced 2024-12-27 09:08:55 +01:00

History

Georgi Gerganov b6c5f49b78 whisper : add batched decoding (#1486 ) * whisper : add whisper_batch * whisper : move kv_self to whisper_state * whisper : full batched decoding support * whisper : fix memory leak in whisper_batch * whisper : fix mem leak again + remove oboslete function * whisper : clear kv cache when using whisper_decode API * whisper : speed-up sampling * whisper : fix decoders initializer * bench : add batch size 5 bench * whisper : add comment about the KV cache size * whisper : add check for max number of decoders * whisper : avoid starting sampling threads with bs=1 * whisper : enable beam-search by default * cuda : sync llama.cpp fixes		2023-11-15 16:12:52 +02:00
..
bench.cpp	whisper : add batched decoding (#1486 )	2023-11-15 16:12:52 +02:00
CMakeLists.txt	cmake : update to 3.19 (#351 )	2023-01-05 21:22:48 +02:00
README.md	bench.wasm : same as "bench" but runs in the browser (#89 )	2022-12-11 11:09:10 +02:00

README.md

bench

A very basic tool for benchmarking the inference performance on your device. The tool simply runs the Encoder part of the transformer on some random audio data and records the execution time. This way we can have an objective comparison of the performance of the model for various setups.

Benchmark results are tracked in the following Github issue: https://github.com/ggerganov/whisper.cpp/issues/89

# build the bench tool
$ make bench

# run it on the small.en model using 4 threads
$ ./bench -m ./models/ggml-small.en.bin -t 4

whisper_model_load: loading model from './models/ggml-small.en.bin'
whisper_model_load: n_vocab       = 51864
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: f16           = 1
whisper_model_load: type          = 3
whisper_model_load: mem_required  = 1048.00 MB
whisper_model_load: adding 1607 extra tokens
whisper_model_load: ggml ctx size = 533.05 MB
whisper_model_load: memory size =    68.48 MB 
whisper_model_load: model size  =   464.44 MB

whisper_print_timings:     load time =   240.82 ms
whisper_print_timings:      mel time =     0.00 ms
whisper_print_timings:   sample time =     0.00 ms
whisper_print_timings:   encode time =  1062.21 ms / 88.52 ms per layer
whisper_print_timings:   decode time =     0.00 ms / 0.00 ms per layer
whisper_print_timings:    total time =  1303.04 ms

system_info: n_threads = 4 | AVX2 = 0 | AVX512 = 0 | NEON = 1 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 1 | 

If you wish, you can submit these results here:

  https://github.com/ggerganov/whisper.cpp/issues/89

Please include the following information:

  - CPU model
  - Operating system
  - Compiler