whisper.cpp

whisper.cpp copied to clipboard

Foreign languages support ?

1

How to download modules for other languages (not English only) ? I seems only English modules can be downloaded ``` # Whisper models models=( "tiny.en" "tiny" "base.en" "base" "small.en" "small"...

Ali-Alzyoud

SwiftUI realtime example

4

Hey everyone, The normal [whisper.objc](https://github.com/ggerganov/whisper.cpp/tree/c353100bad5b8420332d2d451323214c84c66950/examples/whisper.objc) example has support for real-time transcription. I am currently in the process of adding this to the [whisper.swiftui](https://github.com/ggerganov/whisper.cpp/tree/c353100bad5b8420332d2d451323214c84c66950/examples/whisper.swiftui) example and wanted to ask if somebody...

lucabeetz

Hello, first of all, congratulations on the package. I have a problem running the Twitch script on Windows using wsl with Ubuntu. Whenever I run it with an online stream,...

PedroRamosRguez

This adds support for the XOP instruction set on AMD processors by including the `x86intrin.h` header file when the `__XOP__` macro is defined.

gtreshchev

I have trouble to load module.FS_createDataFile in 'whisper.cpp/examples/whisper.wasm/index-tmpl.html'

1

 first, i have cors issue then i locate model bin file in local path and rework. Incidentally i copy index-tmpl.html to php file and i add cors allow header...

cdi2303

First of all thank @ggerganov for creating such a useful project! super helpful! it would be nice if the program can output a json file that contains detailed info of...

eisneim

Hi! It would be nice to be able to register some log-handler to get the output of the transcription process in the golang binding. Right now it is just printing...

KopiasCsaba

Hello! Thank you very much for this awesome work in here. I think it would be nice to have a way to stop the processing, when it comes to the...

KopiasCsaba

llama_model_load: invalid model file './models/ggml-small.en.bin' (too old, regenerate your model files!)

1

I just download the model of ggml-small.en.bin and run the command like this ./talk-llama -mw ./models/for-tests-ggml-small.bin -ml ./models/ggml-small.en.bin -p "Georgi" -t 8 the error message : llama_model_load: invalid model file...

parkerqian

talk-llama segmentation fault on mac os

1

# there is no file named ggml-model-q4_0.bin llama_model_load: loading model from './models/7B/ggml-model-q4_0.bin' - please wait ... llama_model_load: failed to open './models/7B/ggml-model-q4_0.bin' llama_init_from_file: failed to load model main: processing, 8 threads,...

starsea