Whisper
Whisper copied to clipboard
Const-me
High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model
I was not having much luck with diarisation using the SDK so I moved to Stereo recordings where each channel is a side of a conversation. Does anyone know how...
When I do main.exe -m ggml-base.bin -f 1.wav 2.wav 3.wav 1.wav 2.wav where wav1 = 1,2,3 (I count and record it in 16bit wav file) wav2 = 4,5,6 wav3 =...
I use the GUI to process long time audio(>20min), it only outputs 50% of the normal output, for other output is duplicate. I try use medium and large model, but...
Hello, would it be possible to add an option for timemark / speaker? Would be an nice setup for interview.
I found the cli release have the option `--output-words` which should normally generate a wts file, but it don't work, --- Then I tested [whisper.cpp](https://github.com/ggerganov/whisper.cpp) release, and it worked, generated...
Could you please make the app describe all the videos in a folder by one click? even the subfolder. Thank you.
Seems like the winsper.cpp project has an example of realtime transcription using C++. Is it possible to port the same logic to C# using yor implementation of D3D? And a...
Currently, the realtime transcript has a noticeable latency > In the current version there’s high latency for realtime audio capture. > Specifically, depending on voice detection the figure is about...
in which would be this one https://github.com/guillaumekln/faster-whisper
