Update README.md

README.md

@@ -20,7 +20,7 @@ metrics:
 # Description
 
 This model is a Reward Model trained on the [RobotsMali transcription scorer dataset](https://huggingface.co/datasets/RobotsMali/transcription-scorer), where the scores were assigned by human annotators.  
-It predicts a continuous score between 0 and 1 for a pair (audio, text), representing how well the text matches the spoken audio.
+It predicts a continuous score between 0 and 1 for a pair (**audio**, **text**), representing how well the text matches the spoken audio.
 
 The model can be integrated as a Reward Model within RLHF pipelines to evaluate or fine-tune ASR models based on human preference scores.
 
@@ -34,7 +34,7 @@ The model consists of two main encoders — one for audio and one for text — f
 ### Audio Encoder
 
 Input: Raw waveform (16 kHz)  
-Feature extraction: Mel-spectrogram computed from waveform using WhisperFeatureExtractor
+Feature extraction: Mel-spectrogram computed from waveform using ***WhisperFeatureExtractor***
 
 Parameters:
 - n_fft: 1024