Spaces:
Running
Running
docs : document how to use 'WHISPER_FFMPEG' build option (#3029)
Browse filesFFmpeg integration was introduced in 1b51fdf by William Tambellini,
but not mentioned in the main documentation.
Add a short guide on how to enable the feature. Confirmed to work
on both Ubuntu 24.04 and Fedora 39.
Signed-off-by: Fujimoto Seiji <[email protected]>
README.md
CHANGED
|
@@ -375,6 +375,37 @@ Run the inference examples as usual, for example:
|
|
| 375 |
- If you have trouble with Ascend NPU device, please create a issue with **[CANN]** prefix/tag.
|
| 376 |
- If you run successfully with your Ascend NPU device, please help update the table `Verified devices`.
|
| 377 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 378 |
## Docker
|
| 379 |
|
| 380 |
### Prerequisites
|
|
|
|
| 375 |
- If you have trouble with Ascend NPU device, please create a issue with **[CANN]** prefix/tag.
|
| 376 |
- If you run successfully with your Ascend NPU device, please help update the table `Verified devices`.
|
| 377 |
|
| 378 |
+
## FFmpeg support (Linux only)
|
| 379 |
+
|
| 380 |
+
If you want to support more audio formats (such as Opus and AAC), you can turn on the `WHISPER_FFMPEG` build flag to enable FFmpeg integration.
|
| 381 |
+
|
| 382 |
+
First, you need to install required libraries:
|
| 383 |
+
|
| 384 |
+
```bash
|
| 385 |
+
# Debian/Ubuntu
|
| 386 |
+
sudo apt install libavcodec-dev libavformat-dev libavutil-dev
|
| 387 |
+
|
| 388 |
+
# RHEL/Fedora
|
| 389 |
+
sudo dnf install libavcodec-free-devel libavformat-free-devel libavutil-free-devel
|
| 390 |
+
```
|
| 391 |
+
|
| 392 |
+
Then you can build the project as follows:
|
| 393 |
+
|
| 394 |
+
```bash
|
| 395 |
+
cmake -B build -D WHISPER_FFMPEG=yes
|
| 396 |
+
cmake --build build
|
| 397 |
+
```
|
| 398 |
+
|
| 399 |
+
Run the following example to confirm it's working:
|
| 400 |
+
|
| 401 |
+
```bash
|
| 402 |
+
# Convert an audio file to Opus format
|
| 403 |
+
ffmpeg -i samples/jfk.wav jfk.opus
|
| 404 |
+
|
| 405 |
+
# Transcribe the audio file
|
| 406 |
+
./build/bin/whisper-cli --model models/ggml-base.en.bin --file jfk.opus
|
| 407 |
+
```
|
| 408 |
+
|
| 409 |
## Docker
|
| 410 |
|
| 411 |
### Prerequisites
|