Update Readme

README.md

@@ -1,38 +1,54 @@
 ---
-language:
-- ja
 license: apache-2.0
+language:
+- vi
 tags:
 - automatic-speech-recognition
-- mozilla-foundation/common_voice_8_0
-- generated_from_trainer
+- robust-speech-event
+- common-voice
+- vi
 model-index:
 - name: wav2vec2-large-xlsr-53-ja
-  results: []
+  results:
+  - task: 
+      name: Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice 8.0
+      type: mozilla-foundation/common_voice_8_0
+      args: ja
+    metrics:
+       - name: Test WER (with LM)
+         type: wer
+         value: 16.08
+       - name: Test CER (with LM)
+         type: cer
+         value: 7.15
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
 # wav2vec2-large-xlsr-53-ja
 
 This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - JA dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.4214
-- Wer: 0.3375
-- Cer: 0.1587
-
-## Model description
 
-More information needed
+### Benchmark WER result:
+| | [COMMON VOICE 7.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_7_0) | [COMMON VOICE 8.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0)
+|---|---|---|---|
+|without LM| 15.74 | 25.10 |
+|with 4-grams LM| 15.37 | 16.09 |
 
-## Intended uses & limitations
+### Benchmark CER result:
+| | [COMMON VOICE 7.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_7_0) | [COMMON VOICE 8.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0)
+|---|---|---|---|
+|without LM| 9.51 | 9.95 |
+|with 4-grams LM| 6.91 | 7.15 |
 
-More information needed
+## Evaluation
 
-## Training and evaluation data
+Please use the eval.py file to run the evaluation:
 
-More information needed
+```python
+python eval.py --model_id vutankiet2901/wav2vec2-large-xlsr-53-ja --dataset mozilla-foundation/common_voice_7_0 --config ja --split test --log_outputs
+```
 
 ## Training procedure