whisper.cpp
whisper.cpp copied to clipboard
ggerganov
Port of OpenAI's Whisper model in C/C++
Adds functions that use `CLOCK_PROCESS_CPUTIME_ID` instead of `CLOCK_MONOTONIC` for timings, and are therefore not affected by other processes on the system. One thing to check before we merge: since the...
I am trying to live captioning a call.
just like https://github.com/ggerganov/whisper.cpp/issues/25, when transcribed in zh(chinese), there are still some characters missing, and the model is from ggml-large.bin in hugging-face(https://huggingface.co/datasets/ggerganov/whisper.cpp/tree/main). Maybe the large model and the large-v1 model still...
For the sake of completion of the POWER port, it would be nice if big endian worked. I made some progress on the primitives involved, but I could use some...
Currently, the `bench` tool simply spits out the timings from `whisper_print_timings`. These timings are not process specific and as such are influenced by other processes on the system. Should we...
It'd be nice to be able to specify a list of languages when passing multiple files to recognize, or to pass a file:lang pairs to let each file be recognized...
Hey there! This is an awesome project, I'm trying to build a web app using this. Unfortunately running into a weird issue. When transcribing 2-3 seconds of audio, M1/M2 Macs...
Attempting to use the `--language auto` option to enable auto-detect with the multi-language model throws an error for the `stream` tool. **Command** ```sh ./stream -m ./models/ggml-base.bin --threads 8 --step 500...
trying to run: node --experimental-wasm-threads --experimental-wasm-simd ../tests/test-whisper.js but get: failed to asynchronously prepare wasm: CompileError: WebAssembly.instantiate(): Compiling function #62 failed: i32x4.splat found empty stack @+5977
