techiaith
/

whisper-base-ft-cv-cy-en-cpp

Automatic Speech Recognition

Model card Files Files and versions Community

DewiBrynJones commited on 24 days ago

Commit

71380ca

•

1 Parent(s): 45b5d99

Update README.md

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -19,8 +19,9 @@ This model is a version of the [openai/whisper-base](https://huggingface.co/open
 [converted for use in whisper.cpp](https://github.com/ggerganov/whisper.cpp/tree/master/models#fine-tuned-models). Whispercpp is
 a C/C++ port of Whisper that provides high performance inference on offline hardware such as desktops, laptops and mobile devices.
-The model is a smaller in size to the corresponding cloud hosted model [techiaith/whisper-large-v3-ft-cv-cy-en](https://huggingface.co/techiaith/whisper-large-v3-ft-cv-cy-en)
-Since the model is smaller in size, it achieves a success rate of 98.34% on detecting the correct language,
 while for transcribing it achieves the following WER results:
  - Welsh: 40.10

 [converted for use in whisper.cpp](https://github.com/ggerganov/whisper.cpp/tree/master/models#fine-tuned-models). Whispercpp is
 a C/C++ port of Whisper that provides high performance inference on offline hardware such as desktops, laptops and mobile devices.
+The model is a smaller in size to the corresponding cloud hosted model
+[techiaith/whisper-large-v3-ft-cv-cy-en](https://huggingface.co/techiaith/whisper-large-v3-ft-cv-cy-en).
+It achieves a success rate of 98.34% on detecting the correct language in speech,
 while for transcribing it achieves the following WER results:
  - Welsh: 40.10