whisper.cpp
whisper.cpp copied to clipboard
ggerganov
Port of OpenAI's Whisper model in C/C++
I noticed that the base model, it is good to recognize the Russian language and immediately transcribes it into en, and the quality of translation on high, if you put...
Please can someone make this support RTL (arabic) properly? or give me a hint how to do it and I will try to code it myself
It would be good to be able to save sessions after transcription Right now, when going back to a file in history, it re-transcribes the audio. But The interface is...
This is an easy one to fix for anyone wanting to contribute. (I can get to it later if nobody else does). If one supplies `-su` as a parameter alongside...
When i run main example, i always get assert: ``` main.exe -m models\ggml-small.bin -f samples\jfk.wav -t 8 whisper_init_from_file_no_state: loading model from 'models\ggml-small.bin' whisper_model_load: loading model whisper_model_load: n_vocab = 51865 whisper_model_load:...
Due to environmental reasons, there are always problems with compilation. So if you can include the compiled main when releasing the version, I would be very grateful
So, I haven't looked in details, but I suspect there might be something wrong in the new `large` model released by OpenAI. Keep in mind this is very anecdotal evidence...
When I use --print-colors, an error message appears. What is the problem? My input is as follows: whisper-ctranslate2 .\test\main.wav --language zh --model large-v2 --device cuda --output_dir .\test\output-ctranslate_cuda_large_v2_float32 --print-colors The error...
Hey man, cool project. Just wanted to let you know I made an npm library based on your project: https://github.com/zwhitchcox/whisper-asr It still needs a lot of work, namely: * better...
Could you please explain why there are many blank lines between the sentences when using the command "`./stream -m ./models/ggml-tiny.en.bin -t 8 --step 500 --length 5000`" with the YouTube video...
