ggerganov

/

whisper.cpp

like 588

I have uploaded the updated large-v3 CoreML model.
https://github.com/ggerganov/whisper.cpp/issues/1437#issuecomment-1807608344

It seems to be working properly according to the operation check logs.

whisper_init_state: loading Core ML model from 'models/ggml-large-v3-encoder.mlmodelc'

./main -m models/ggml-large-v3.bin -f samples/jfk.wav
whisper_init_from_file_with_params_no_state: loading model from 'models/ggml-large-v3.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         = 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_backend_init: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M2
ggml_metal_init: picking default device: Apple M2
ggml_metal_init: default.metallib not found, loading from source
ggml_metal_init: loading '/Users/solaoi/Projects/solaoi/whisper.cpp/ggml-metal.metal'
ggml_metal_init: GPU name:   Apple M2
ggml_metal_init: GPU family: MTLGPUFamilyApple8 (1008)
ggml_metal_init: hasUnifiedMemory              = true
ggml_metal_init: recommendedMaxWorkingSetSize  = 17179.89 MB
ggml_metal_init: maxTransferRate               = built-in GPU
ggml_metal_add_buffer: allocated 'backend         ' buffer, size =  3117.88 MB, ( 3118.40 / 17179.89)
whisper_model_load:    Metal buffer size =  3117.87 MB
whisper_model_load: model size    = 3117.39 MB
whisper_backend_init: using Metal backend
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M2
ggml_metal_init: picking default device: Apple M2
ggml_metal_init: default.metallib not found, loading from source
ggml_metal_init: loading '/Users/solaoi/Projects/solaoi/whisper.cpp/ggml-metal.metal'
ggml_metal_init: GPU name:   Apple M2
ggml_metal_init: GPU family: MTLGPUFamilyApple8 (1008)
ggml_metal_init: hasUnifiedMemory              = true
ggml_metal_init: recommendedMaxWorkingSetSize  = 17179.89 MB
ggml_metal_init: maxTransferRate               = built-in GPU
ggml_metal_add_buffer: allocated 'backend         ' buffer, size =   220.20 MB, ( 3338.60 / 17179.89)
whisper_init_state: kv self size  =  220.20 MB
ggml_metal_add_buffer: allocated 'backend         ' buffer, size =   245.76 MB, ( 3584.36 / 17179.89)
whisper_init_state: kv cross size =  245.76 MB
whisper_init_state: loading Core ML model from 'models/ggml-large-v3-encoder.mlmodelc'
whisper_init_state: first run on a device may take a while ...
whisper_init_state: Core ML model loaded
ggml_metal_add_buffer: allocated 'backend         ' buffer, size =     0.02 MB, ( 3593.88 / 17179.89)
whisper_init_state: compute buffer (conv)   =   10.85 MB
ggml_metal_add_buffer: allocated 'backend         ' buffer, size =     0.02 MB, ( 3593.90 / 17179.89)
whisper_init_state: compute buffer (cross)  =    9.32 MB
ggml_metal_add_buffer: allocated 'backend         ' buffer, size =     0.02 MB, ( 3593.91 / 17179.89)
whisper_init_state: compute buffer (decode) =   99.17 MB
ggml_metal_add_buffer: allocated 'backend         ' buffer, size =     9.22 MB, ( 3603.14 / 17179.89)
ggml_metal_add_buffer: allocated 'backend         ' buffer, size =     7.68 MB, ( 3610.82 / 17179.89)
ggml_metal_add_buffer: allocated 'backend         ' buffer, size =    97.53 MB, ( 3708.35 / 17179.89)

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

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


[00:00:00.300 --> 00:00:09.000]   And so, my fellow Americans, ask not what your country can do for you, ask what you
[00:00:09.000 --> 00:00:11.000]   can do for your country.


whisper_print_timings:     load time =   984.30 ms
whisper_print_timings:     fallbacks =   0 p /   0 h
whisper_print_timings:      mel time =     7.56 ms
whisper_print_timings:   sample time =    81.95 ms /   148 runs (    0.55 ms per run)
whisper_print_timings:   encode time =  1999.00 ms /     1 runs ( 1999.00 ms per run)
whisper_print_timings:   decode time =     0.00 ms /     1 runs (    0.00 ms per run)
whisper_print_timings:   batchd time =  1377.15 ms /   146 runs (    9.43 ms per run)
whisper_print_timings:   prompt time =     0.00 ms /     1 runs (    0.00 ms per run)
whisper_print_timings:    total time =  5798.28 ms
ggml_metal_free: deallocating
ggml_metal_free: deallocating