GGML_ASSERT: \whisper.cpp\ggml.c:3904: !ggml_is_transposed(a)

[ANMahmood]

Trying to simply compile and run talk.exe on Windows 10.
Also, I checked out the talk.llama branch but msbuild produced errors. Is there a shortcut way to test talk.llama ?

.\whisper.cpp> cmake -S . -B ./build -A x64 -DCMAKE_BUILD_TYPE=Release -DWHISPER_SUPPORT_SDL2=ON -DWHISPER_BUILD_EXAMPLES=ON -DWHISPER_BUILD_TESTS=ON -DWHISPER_PERF=ON

.\whisper.cpp> msbuild ALL_BUILD.vcxproj -t:build -p:configuration=Release -p:platform=x64

cp ./sdl2/SDL2-2.26.0/lib/x64/SDL2.dll build/bin/Release

.\whisper.cpp> .\build\bin\Release\talk.exe -p Santa -mw .\models\ggml-base.en.bin

whisper_init_from_file_no_state: loading model from '.\models\ggml-base.en.bin'
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: f16 = 1
whisper_model_load: type = 2
whisper_model_load: mem required = 215.00 MB (+ 6.00 MB per decoder)
whisper_model_load: adding 1607 extra tokens
whisper_model_load: model ctx = 140.60 MB
whisper_model_load: model size = 140.54 MB
whisper_init_state: kv self size = 5.25 MB
whisper_init_state: kv cross size = 17.58 MB
gpt2_model_load: loading model from 'models/ggml-gpt-2-117M.bin'
gpt2_model_load: n_vocab = 50257
gpt2_model_load: n_ctx = 1024
gpt2_model_load: n_embd = 768
gpt2_model_load: n_head = 12
gpt2_model_load: n_layer = 12
gpt2_model_load: f16 = 1
gpt2_model_load: ggml ctx size = 311.12 MB
gpt2_model_load: memory size = 72.00 MB, n_mem = 12288
gpt2_model_load: model size = 239.08 MB
gpt-2: model loaded in 217 ms

SDL_main: processing, 4 threads, lang = en, task = transcribe, timestamps = 0 ...

init: found 3 capture devices:
init: - Capture device #0: 'Microphone Array (Realtek(R) Audio)'
init: - Capture device #1: 'Microphone (USB Audio Device)'
init: - Capture device #2: 'Microphone (Webcam 250)'
init: attempt to open default capture device ...
init: obtained spec for input device (SDL Id = 2):
init: - sample rate: 16000
init: - format: 33056 (required: 33056)
init: - channels: 1 (required: 1)
init: - samples per frame: 1024
gpt-2: prompt:

This is a dialogue between Santa (A) and a person (B). The dialogue so far is:

B: Hello Santa, how are you?
A: I'm fine, thank you.
{1}
Here is how Santa (A) continues the dialogue:

A:

SDL_main: Speech detected! Processing ...
SDL_main: Heard nothing, skipping ...
SDL_main: Speech detected! Processing ...
SDL_main: Heard '←[1mHello?←[0m', (t = 3501 ms)
GGML_ASSERT: \whisper.cpp\ggml.c:3904: !ggml_is_transposed(a)

[includedhj]

same question

[ggerganov]

Should be fixed now