whisper android demo issues

[skyxiaobai]

Any possible to inprovement less 10s when used tiny bin ? Piexl 7 android devices.

System Info: 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 |
Loading data...
Copying jfk.wav...
All data copied to working directory.
Loading model...
Loaded model ggml-base.bin.
Reading wave samples... 11001 ms
Transcribing data...
Done (30141 ms): And so my fellow Americans, ask not what your country can do for you, ask what you can do for your country.

[litongjava]

The default model is

Loaded model ggml-base.bin.

you can swith to tiny bin and test it again

[skyxiaobai]

tiny bin testing is 14s, but still fell slowly, android devices include GPU(QC chipset), whether we can used this to improvements again ? Any suggestions ? CPU-only execution seems hard to speed up again .

[litongjava]

It is possible to use gpu reasoning, you need to add a parameter to specify the gpu, but I haven't tested it.

…

On Wed, Dec 13, 2023, 9:53 PM skyxiaobai ***@***.***> wrote: tiny bin testing is 14s, but still fell slowly, android devices include GPU(QC chipset), whether we can used this to improvements again ? Any suggestions ? CPU-only execution seems hard to speed up again . — Reply to this email directly, view it on GitHub <#1 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AHSKMPMIZO2M6C3OJMOCDHTYJKV7ZAVCNFSM6AAAAABAUMHJY6VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTQNJVGM2DOOJWHE> . You are receiving this because you commented.Message ID: ***@***.***>

[lxwboxs]

May I ask which parameter controls the inference using GPU? I couldn't find it, can you tell me where it is? How should I operate it specifically