Georgi Gerganov

Here is one way to achieve this: ```bash # build shared libwhisper.so gcc -O3 -std=c11 -pthread -mavx -mavx2 -mfma -mf16c -fPIC -c ggml.c g++ -O3 -std=c++11 -pthread --shared -fPIC -static-libstdc++...

Yeah, the `ctx` pointer wasn't being passed properly. I've updated the python script above. Give it another try - I think it should work now.

Breaking changes in the C-api in last commit: e30cf831584a9b96df51849302de8bb35c5709ee

The `WhisperFullParams` struct has been updated since I posted, so you have to match the new struct in the [whisper.h](https://github.com/ggerganov/whisper.cpp/blob/0e689f83d8049f2d532f9778827d61b7db2a2c77/whisper.h#L184-L218). Ideally, the python bindings should be automatically generated based on...

The `prompt_past` member of the context contains the tokens that have been decoded so far during the transcription: https://github.com/ggerganov/whisper.cpp/blob/a6c786d5dccf5f54a92da890f70715b4c9831172/whisper.cpp#L2388-L2392 Currently, it is empty when we start processing an audio and...

@lerela @ArtyomZemlyak Just pushed another version - I'm doing this blindly, so not sure if it works

@jaybinks Just pushed another fix

I found a machine with AVX-512 CPU and fixed the code. It now produces correct results, but the performance compared to AVX2 is worse. Either I am not utilising correctly...

Adding GPU support is not out of the question, but it's low priority atm. Here are some additional thoughts on this: https://github.com/ggerganov/whisper.cpp/discussions/126

@nyadla-sys Thanks for the contribution! Unfortunately @randomeizer is correct - adding GPL code to this project is not possible because this will make the project also GPL and I don't...