Run success on Atlas 300I Duo(Ascend NPU)

[gzqccnu]

output:

./build/bin/whisper-cli -f samples/jfk.wav -m models/ggml-base.en.bin -t 8
whisper_init_from_file_with_params_no_state: loading model from 'models/ggml-base.en.bin'
whisper_init_with_params_no_state: use gpu    = 1
whisper_init_with_params_no_state: flash attn = 1
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw        = 0
whisper_init_with_params_no_state: devices    = 3
whisper_init_with_params_no_state: backends   = 2
whisper_model_load: loading model
whisper_model_load: n_vocab       = 51864
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         = 1
whisper_model_load: qntvr         = 0
whisper_model_load: type          = 2 (base)
whisper_model_load: adding 1607 extra tokens
whisper_model_load: n_langs       = 99
whisper_model_load:        CANN0 total size =   147.37 MB
whisper_model_load: model size    =  147.37 MB
whisper_backend_init_gpu: device 0: CANN0 (type: 1)
whisper_backend_init_gpu: found GPU device 0: CANN0 (type: 1, cnt: 0)
whisper_backend_init_gpu: using CANN0 backend
ggml_backend_cann_context: device 0 async operator submission is OFF
whisper_init_state: kv self size  =    6.29 MB
whisper_init_state: kv cross size =   18.87 MB
whisper_init_state: kv pad  size  =    3.15 MB
whisper_init_state: compute buffer (conv)   =   17.24 MB
whisper_init_state: compute buffer (encode) =   32.38 MB
whisper_init_state: compute buffer (cross)  =    4.66 MB
whisper_init_state: compute buffer (decode) =  101.94 MB

system_info: n_threads = 8 / 64 | WHISPER : COREML = 0 | OPENVINO = 0 | CPU : NEON = 1 | ARM_FMA = 1 | FP16_VA = 1 | DOTPROD = 1 | OPENMP = 1 | REPACK = 1 |

main: processing 'samples/jfk.wav' (176000 samples, 11.0 sec), 8 threads, 1 processors, 5 beams + best of 5, lang = en, task = transcribe, timestamps = 1 ...

new_pool_for_device: device 0 use vmm pool

[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 =   164.00 ms
whisper_print_timings:     fallbacks =   0 p /   0 h
whisper_print_timings:      mel time =     9.92 ms
whisper_print_timings:   sample time =    88.04 ms /   133 runs (     0.66 ms per run)
whisper_print_timings:   encode time =  1629.87 ms /     1 runs (  1629.87 ms per run)
whisper_print_timings:   decode time =    76.30 ms /     3 runs (    25.43 ms per run)
whisper_print_timings:   batchd time =   599.22 ms /   126 runs (     4.76 ms per run)
whisper_print_timings:   prompt time =     0.00 ms /     1 runs (     0.00 ms per run)
whisper_print_timings:    total time =  2585.82 ms

NPU INFO:

+--------------------------------------------------------------------------------------------------------+
| npu-smi 25.2.0                                   Version: 25.2.0                                       |
+-------------------------------+-----------------+------------------------------------------------------+
| NPU     Name                  | Health          | Power(W)     Temp(C)           Hugepages-Usage(page) |
| Chip    Device                | Bus-Id          | AICore(%)    Memory-Usage(MB)                        |
+===============================+=================+======================================================+
| 2       310P3                 | OK              | NA           45                0     / 0             |
| 0       0                     | 0000:01:00.0    | 0            1531 / 44280                            |
+-------------------------------+-----------------+------------------------------------------------------+
| 2       310P3                 | OK              | NA           43                0     / 0             |
| 1       1                     | 0000:01:00.0    | 0            1410 / 43693                            |
+===============================+=================+======================================================+
+-------------------------------+-----------------+------------------------------------------------------+
| NPU     Chip                  | Process id      | Process name             | Process memory(MB)        |
+===============================+=================+======================================================+
| No running processes found in NPU 2                                                                    |
+===============================+=================+======================================================+

Actually my npu is Atlas 300I Duo