Update README.md

README.md

@@ -12,7 +12,7 @@ This repository contains all the models and datasets for train/evaluate the Japa
 Following table shows CER comparison with different data size of ReazonSpeech used to distill [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3). The model names follows
 `japanese-asr/distil-whisper-large-v3-ja-reazonspeech-{size of reazonspeech}`.
 
-### CER (Normalized)
+***CER (Normalized)***: Normalized CER is the commonly used metric for Japanese ASR, where the punctuations and special characters are ignored.
 | model                                                                                                                                             |   [CommonVoice 8.0](https://huggingface.co/datasets/japanese-asr/ja_asr.common_voice_8_0) |   [JSUT basic5000](https://huggingface.co/datasets/japanese-asr/ja_asr.jsut_basic5000) |   [ReazonSpeech Test](https://huggingface.co/datasets/japanese-asr/ja_asr.reazonspeech_test) |
 |:--------------------------------------------------------------------------------------------------------------------------------------------------|-------------------:|-----------------:|--------------------:|
 | [japanese-asr/distil-whisper-large-v3-ja-reazonspeech-all](https://huggingface.co/japanese-asr/distil-whisper-large-v3-ja-reazonspeech-all)       |               9.20 |             8.40 |               11.63 |
@@ -29,7 +29,7 @@ Following table shows CER comparison with different data size of ReazonSpeech us
 | [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny)                                                                                 |              46.86 |            35.69 |               96.69 |
 | [reazon-research/reazonspeech-nemo-v2](https://huggingface.co/reazon-research/reazonspeech-nemo-v2)                                               |               9.07 |             7.43 |               11.17 |
 
-### CER (Raw)
+***CER (Raw)***: In contrast to the normalized CER, raw CER is namely the CER computed over the raw prediction and label without any normalizaion.
 | model                                                                                                                                             |   [CommonVoice 8.0](https://huggingface.co/datasets/japanese-asr/ja_asr.common_voice_8_0) |   [JSUT basic5000](https://huggingface.co/datasets/japanese-asr/ja_asr.jsut_basic5000) |   [ReazonSpeech Test](https://huggingface.co/datasets/japanese-asr/ja_asr.reazonspeech_test) |
 |:------------------------------------------------------------|---------------------------------------:|-------------------------------------:|----------------------------------------:|
 | [japanese-asr/distil-whisper-large-v3-ja-reazonspeech-all](https://huggingface.co/japanese-asr/distil-whisper-large-v3-ja-reazonspeech-all)    |                                   15.4 |                                 15.4 |                                    17.4 |