examples : add wer cli example #2990
Draft
+375
−0
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ggerganov
reviewed
Apr 2, 2025
This commit add as suggestion for a Word Error Rate calculation
example.
The motivation for this is that this could be used for WER testing.
Usage:
```console
$ ./build/bin/whisper-wer
Usage: ./build/bin/whisper-wer [options]
Options:
-r, --reference PATH Full path to reference transcriptions directory
-a, --actual PATH Full path to actual transcriptions directory
--help Display this help message
```
Example usage:
```console
$ ./build/bin/whisper-wer -r examples/wer/reference_transcriptions/ \
-a examples/wer/actual_transcriptions/
Word Error Rate for : jfk.wav.txt
Reference words: 22
Actual words: 22
Substitutions: 1
Deletions: 0
Insertions: 0
Total edits: 1
WER: 0.045455
```
A more detailed description can be found in examples/wer/README.md.
A unit test is provided in tests/test-wer.cpp.
```console
$ cmake --build build --target test-wer && \
ctest -R test-wer --test-dir build --output-on-failure
```
This commit adds the C++17 standard to the CMakeLists.txt file. The motivatiion for this is that ggml sets this and it would seem alright to have the same standard in whisper too.
This commit adds pthread to the test-wer target for FreeBSD. This is necessary to avoid the following error: ```console [68%] Linking CXX executable ../bin/test-wer ld: error: undefined reference due to --no-allow-shlib-undefined: pthread_create >>> referenced by ../src/libwhisper.so.1.7.4 c++: error: linker command failed with exit code 1 (use -v to see invocation) gmake[2]: *** [tests/CMakeFiles/test-wer.dir/build.make:106: bin/test-wer] Error 1 gmake[1]: *** [CMakeFiles/Makefile2:1421: tests/CMakeFiles/test-wer.dir/all] Error 2 ``` Refs: https://github.com/ggerganov/whisper.cpp/actions/runs/14218829646/job/39841747819
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This commit add as suggestion for a Word Error Rate calculation example.
The motivation for this is that this could be used for WER testing. Usage:
Example usage:
A more detailed description can be found in examples/wer/README.md.
A unit test is provided in tests/test-wer.cpp.