whisper.cpp
whisper.cpp copied to clipboard
ggerganov
Port of OpenAI's Whisper model in C/C++
Some audio files randomly take forever to transcribe on my M1 built of today’s main branch. My benchmark for small.en shows a fast encoding speed of ~800ms. Full benchmark {0:59}~/projects/whisper.cpp:master...
**What's wrong:** Each line has a prepended space before the line begins. **What I want:** I want each line to begin with no extra spaces. **Supporting details:** Here's what I...
Hello! As previously mentioned elsewhere (https://mastodon.social/@byterhymer/109989882945679282 for reference) I would like to make an effort at creating a MacPort Portfile for whisper.cpp given my recent overwhelmingly positive experience with building...
I would like to just generate subtitles once and then translate them into other languages instead of running the whole lengthy process from scratch for each language one by one....
Hi @ggerganov, we've discussed this in https://github.com/ggerganov/whisper.cpp/issues/7 a bit but I think its worth to create an extra issue to keep track of it. In my tests on Raspberry Pi...
It seems there's an error from sysctl which is on the right path: /usr/sbin/sysctl. Make warns about fall back on libraries. I'm not very savvy compiling on mac, clearly. This...
every once in a while i am getting an error that just states "libc++abi: terminating with uncaught exception of type std::length_error: vector" I am using whisper through node.js and calling...
How about an option of your (fantastic) llama.cpp repo to swap out GPT-2?
I'm following the instructions in #168 but with version `1.2.1` I can no longer compile successfully: I start in a fresh Debian container and I prep it by doing: ```...
