whisper.cpp
whisper.cpp copied to clipboard
Port of OpenAI's Whisper model in C/C++
I've been working on a Go service that lives inside a Docker container and I have a working setup for this: building the whisper.cpp library and integrating it into my...
I am planning to use M1 Max to work as the transcription API server for some web applications. When I am following the examples in the https://github.com/ggerganov/whisper.cpp/tree/master/examples/server I have a...
Using --max-len and --split on word when generating an SRT file generate "empty subtitles", meaning sentences that appear for 0 seconds. I had 3 such occurrences in a 7-minute sample....
I tried release 1.4.0 and release 1.5.4 to process a 2.5 min audio. Release 1.5.4 is 11s slower than release 1.4.0. Latest whisper.cpp code runs even more slower. Is this...
Is this expected? I'm on master, commit hash: `59119f4f20b27` Machine: Apple M1 Pro, 14-inch, Sonoma 14.3.1 Logs: ``` whisper_init_from_file_with_params_no_state: loading model from 'ggml-large-v2.bin' whisper_model_load: loading model whisper_model_load: n_vocab = 51865...
worte some documentation on for dependencies needed for builing on fedora linux.
A cool feature that might be worth exploring would be allowing users to translate to any target language, rather than just english. It is known that whisper was trained to...
I'm hoping to make some bilingual subtitles for my videos, it would be great if you can add this feature, or hopefully real-time transcription + translation in the future. Thanks...
## Output in the console is weird wrong encoding gibberish for Japanese  ## Meanwhile the transcriptions it produces are as expected This is the exact same transcription 
Hello, I’m working with whisper.cpp and ran into a problem where my Japanese audio file is being transcribed into English, despite specifying the input language as Japanese using the -l...