mirror/whisper.cpp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Georgi Gerganov 2022-09-29 23:37:59 +03:00 committed by GitHub
parent 5877c3578e
commit fd3f3d748f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@ -26,7 +26,7 @@ bash ./download-ggml-model.sh base.en
For a quick demo, simply run `make base.en`: For a quick demo, simply run `make base.en`:
```bash ```java
$ make base.en $ make base.en
gcc -pthread -O3 -mavx -mavx2 -mfma -mf16c -c ggml.c gcc -pthread -O3 -mavx -mavx2 -mfma -mf16c -c ggml.c
@ -123,13 +123,13 @@ For detailed usage instructions, run: `./main -h`
Note that `whisper.cpp` runs only with 16-bit WAV files, so make sure to convert your input before running the tool. 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: For example, you can use `ffmpeg` like this:
```bash ```java
ffmpeg -i input.mp3 -ar 16000 -ac 1 -c:a pcm_s16le output.wav 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: 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:
```bash ```java
$ ./main -m models/ggml-medium.en.bin -f samples/gb1.wav -t 8 $ ./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: loading model from 'models/ggml-medium.en.bin'
whisper_model_load: n_vocab = 51864 whisper_model_load: n_vocab = 51864