ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2024-12-18 20:27:53 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Georgi Gerganov 2022-10-25 20:43:10 +03:00
parent 91dcf5f35b
commit 89d8ee3ee5
1 changed files with 12 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
README.md
View File

@ -135,7 +135,7 @@ The command downloads the `base.en` model converted to custom `ggml` format and
For detailed usage instructions, run: `./main -h`
Note that `whisper.cpp` currently runs only with 16-bit WAV files, so make sure to convert your input before running the tool.
Note that the [main](examples/main) example currently 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:
```java
@ -171,6 +171,9 @@ make large
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 about half a minute on a MacBook M1 Pro, using `medium.en` model:
<details>
<summary>Expand to see the result</summary>
```java
$ ./main -m models/ggml-medium.en.bin -f samples/gb1.wav -t 8
@ -237,6 +240,7 @@ whisper_print_timings: encode time = 19552.61 ms / 814.69 ms per layer
whisper_print_timings: decode time = 13249.96 ms / 552.08 ms per layer
whisper_print_timings: total time = 33686.27 ms
```
</details>
## Real-time audio input example
@ -250,18 +254,6 @@ More info is available in [issue #10](https://github.com/ggerganov/whisper.cpp/i
https://user-images.githubusercontent.com/1991296/194935793-76afede7-cfa8-48d8-a80f-28ba83be7d09.mp4
The [stream](examples/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
```
## Confidence color-coding
Adding the `--print-colors` argument will print the transcribed text using an experimental color coding strategy
@ -306,6 +298,13 @@ the Accelerate framework utilizes the special-purpose AMX coprocessor available
| medium | 1.5 GB | ~2.6 GB |
| large | 2.9 GB | ~4.7 GB |
## Benchmarks
In order to have an objective comparison of the performance of the inference across different system configurations,
use the [bench](examples/bench) tool. The tool simply runs the Encoder part of the model and prints how much time it
took to execute it. The results are summarized in the following Github issue:
[Benchmark results](https://github.com/ggerganov/whisper.cpp/issues/89)
## ggml format