whisper.cpp
whisper.cpp copied to clipboard
Port of OpenAI's Whisper model in C/C++
So for spot checking long transcriptions, it would be helpful to have the confidence score output to some file.. either as an extra column in the CSV or maybe some...
Just had an idea for a new example app that allows you to make Chess moves using voice. The example will run in a web-page and will be based on...
### Discussed in https://github.com/ggerganov/whisper.cpp/discussions/206 Originally posted by **ggerganov** January 19, 2023 It should be possible. Here: https://github.com/ggerganov/whisper.cpp/blob/1290fc64572f434f2f36721d2e2b0913cec0178a/whisper.cpp#L3631-L3634 Instead of taking all decoded tokens and advancing with the full 30s window,...
I wanted to create a separate issue for the problems I described in #354. Since 385236d1d3d7a0228f5279657938ae5f1313ca94, I have seen severe regression in WER for noisy audio, at around 10-20%. I...
I would like to start by saying a big thank you for all the work that you put into maintaining and developing this project. My issue is with regards to...
Platform: Windows C++ app built with VS2022. My PC is a Dell laptop with quad core i5. Pass a 3 second audio clip of the word "six" 3 or four...
the path to openblas libraries is hardcoded as: /usr/local/include/openblas a la: ``` ifdef WHISPER_OPENBLAS CFLAGS += -DGGML_USE_OPENBLAS -I/usr/local/include/openblas LDFLAGS += -lopenblas endif ``` As I wish to give whisper.cpp all...
See notebook, section "Word-level timestamps using attention weights": https://github.com/openai/whisper/blob/main/notebooks/Multilingual_ASR.ipynb
First, thank you for your awesome project – a great value to society! I am using the SRT mode output and discovered that a leading space is always added to...