whisper.cpp icon indicating copy to clipboard operation
whisper.cpp copied to clipboard

Port of OpenAI's Whisper model in C/C++

Results 525 whisper.cpp issues
Sort by recently updated
recently updated
newest added

I follow the steps here: https://github.com/ggerganov/whisper.cpp#core-ml-support and ran ``` ./models/generate-coreml-model.sh medium ``` I tried a few times and let it run for about 1 hour but the process typically hung...

I know the repeating segment 'hallucination' was reported multiple times in the past - I've read through most of it and didn't find a solution.   The issue: whisper is outputting...

SPM forbids depending on packages by version string if they have unsafe build flags. The only way to use a package with unsafe flags is by specifying the exact commit...

I'm testing on large.v2 Here's the command `./main -m models/ggml-large-v2.bin -f samples/jfk.wav -dtw large.v2 -ojf -pp -ls` Here's the JSON output, I've removed timestamps for clarity as they match offsets....

K80 is a very old GPU, is it supported in whipper.cpp? This is my NVIDIA driver version, CUDA version, and GCC/G++version NVIDIA driver version:471.11 CUDA version:11.4.0 gcc version:13.2.0 g++ version:13.2.0...

according to the manual, i just wanna speed up inference on the CPU via OpenVINO, however got the problem as bellow. (openvino_conv_env) [root@zaozhuang3L-C6-35 whisper.cpp]# ./main -m models/ggml-base.en-encoder-openvino.bin -f samples/jfk.wav whisper_init_from_file_no_state:...

question

Here are my logs, am I missing something obvious? ``` ❯ make clean I whisper.cpp build info: I UNAME_S: Darwin I UNAME_P: arm I UNAME_M: arm64 I CFLAGS: -I. -O3...

Hi, Generating transcript from English with some video-tech language and tried to use "Initial prompt" to help with the result. Prompt used was; "Rec.709, Rec.2020, 4:2:2, P3, 4:2:0, Ninja, AtomOS,...

Transcriptions are including things such as "Music Playing" and "Bell Rings". Am I missing something silly here or does this param just not work? Using the Swift package fyi

I have gotten many reports that the large v3 model repeats sentences much more often than v2. I'm not sure if there's anything Whisper.cpp can do about this.

question