Update README.md

README.md

@@ -1,3 +1,27 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+datasets:
+- techiaith/commonvoice_18_0_cy_en
+language:
+- cy
+- en
+base_model:
+- openai/whisper-base
+pipeline_tag: automatic-speech-recognition
+tags:
+- whisper.cpp
+---
+
+# whisper-base-ft-cv-cy-en-cpp
+
+This model is a version of the [openai/whisper-base](https://huggingface.co/openai/whisper-base) model, fine-tuned on the 
+[techiaith/commonvoice_18_0_cy_en](https://huggingface.co/datasets/techiaith/commonvoice_18_0_cy_en) dataset, and then 
+[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
+ - English: 30.9