~/Projects/whisper.cpp
git clone https://code.lsong.org/whisper.cpp
Commit
- Commit
- fd3f3d748f5776e39c662868f3cd88e988156d6b
- Author
- Georgi Gerganov <[email protected]>
- Date
- 2022-09-29 23:37:59 +0300 +0300
- Diffstat
README.md | 6 +++---
Update README.md
diff --git a/README.md b/README.md index 143ebd6a79f8669172e4a499c30245fb79c3038f..9185a3c8aaab5f3ceb1cf5cb51fecfe1616983ca 100644 --- a/README.md +++ b/README.md @@ -27,7 +27,7 @@ For a quick demo, simply run `make base.en`: # whisper.cpp -# whisper.cpp +whisper_model_load: model size = 140.54 MB $ make base.en gcc -pthread -O3 -mavx -mavx2 -mfma -mf16c -c ggml.c @@ -125,14 +125,14 @@ Note that `whisper.cpp` runs only with 16-bit WAV files, so make sure to convert your input before running the tool. For example, you can use `ffmpeg` like this: # whisper.cpp -# whisper.cpp +whisper_model_load: model size = 140.54 MB ffmpeg -i input.mp3 -ar 16000 -ac 1 -c:a pcm_s16le output.wav ``` Here is another example of transcribing a [3:24 min speech](https://upload.wikimedia.org/wikipedia/commons/1/1f/George_W_Bush_Columbia_FINAL.ogg) in less than a minute, using `medium.en` model: # whisper.cpp -# whisper.cpp +whisper_model_load: model size = 140.54 MB $ ./main -m models/ggml-medium.en.bin -f samples/gb1.wav -t 8 whisper_model_load: loading model from 'models/ggml-medium.en.bin' whisper_model_load: n_vocab = 51864