Update README.md

Add eval results on dev data.

README.md

@@ -27,7 +27,20 @@ model-index:
        - name: Test CER
          type: cer
          value: 23.64
-
+  - task:
+      name: Automatic Speech Recognition 
+      type: automatic-speech-recognition
+    dataset:
+      name: Robust Speech Event - Dev Data
+      type: speech-recognition-community-v2/dev_data
+      args: de
+    metrics:
+       - name: Test WER
+         type: wer
+         value: 1.0
+       - name: Test CER
+         type: cer
+         value: 30.99
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -37,7 +50,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - JA dataset.
 
-Kanji are converted into Hiragana using the [pykakasi](https://pykakasi.readthedocs.io/en/latest/index.html) library during training and evaluation. The model can output both Hiragana and Katakana characters.
+Kanji are converted into Hiragana using the [pykakasi](https://pykakasi.readthedocs.io/en/latest/index.html) library during training and evaluation. The model can output both Hiragana and Katakana characters. Since there is no spacing, WER is not a suitable metric for evaluating performance and CER is more suitable.
+
+On mozilla-foundation/common_voice_8_0 it achieved:
+- cer: 23.64%
+
+On speech-recognition-community-v2/dev_data it achieved:
+- cer: 30.99%
 
 It achieves the following results on the evaluation set:
 - Loss: 0.5212
@@ -98,4 +117,10 @@ The following hyperparameters were used during training:
 
 ```bash
 python ./eval.py --model_id AndrewMcDowell/wav2vec2-xls-r-300m-japanese --dataset mozilla-foundation/common_voice_8_0 --config ja --split test --log_outputs
+```
+
+2. To evaluate on `mozilla-foundation/common_voice_8_0` with split `test`
+
+```bash
+python ./eval.py --model_id AndrewMcDowell/wav2vec2-xls-r-300m-japanese --dataset speech-recognition-community-v2/dev_data --config de --split validation --chunk_length_s 5.0 --stride_length_s 1.0
 ```