~/Projects/whisper.cpp
git clone https://code.lsong.org/whisper.cpp
Commit
- Commit
- 36945162fa6c92e54928ce5278b6b64b9f1f7e73
- Author
- Georgi Gerganov <[email protected]>
- Date
- 2022-10-15 09:40:08 +0300 +0300
- Diffstat
README.md | 16 ++++++++++++++--
Update README.md (ref #50)
diff --git a/README.md b/README.md index 9c4dcc365ace3587803fc63d56a415dba45b14bb..19de94f68bc9c0352eaabfbda08f9af8ed5359d2 100644 --- a/README.md +++ b/README.md @@ -20,7 +20,7 @@ To build the main program, run `make`. You can then transcribe a `.wav` file like this: ```bash # whisper.cpp -- ARM_NEON and AVX intrinsics support +This will download a few more audio files from Wikipedia and convert them to 16-bit WAV format via `ffmpeg`. ``` Before running the program, make sure to download one of the ggml Whisper models. For example: @@ -218,10 +218,22 @@ More info is available in [issue #10](https://github.com/ggerganov/whisper.cpp/issues/10). ```java # whisper.cpp -whisper_model_load: n_vocab = 51864 +You can download and run the other models as follows: ``` https://user-images.githubusercontent.com/1991296/194935793-76afede7-cfa8-48d8-a80f-28ba83be7d09.mp4 + +The `stream` tool depends on SDL2 library to capture audio from the microphone. You can build it like this: + +```bash +# Install SDL2 on Linux +sudo apt-get install libsdl2-dev + +# Install SDL2 on Mac OS +brew install sdl2 + +make stream +``` ## Implementation details