Update README.md

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
        - name: Test CER
          type: cer
-         value: 43.00
+         value: 41.99
 ---
 
 # Wav2Vec2-Large-XLSR-53-Chinese-zh-cn-gpt
@@ -114,7 +114,7 @@ processor = Wav2Vec2Processor.from_pretrained("ydshieh/wav2vec2-large-xlsr-53-ch
 model = Wav2Vec2ForCTC.from_pretrained("ydshieh/wav2vec2-large-xlsr-53-chinese-zh-cn-gpt")
 model.to("cuda")
 
-chars_to_ignore_regex = '[\,\?\.\!\-\;\:"\“\%\‘\”\�\．\⋯\！\－\：\–\。\》\,\）\,\？\；\～\~\…\︰\，\（\」\‧\《\﹔\、\—\／\,\「\﹖\·\×\̃\̌\ε\λ\μ\и\т\─\□\〈\〉\『\』\ア\オ\カ\チ\ド\ベ\ャ\ヤ\ン\・\丶\ａ\ｂ\ｆ\ｇ\ｉ\ｎ\ｐ\ｔ' + "\']"
+chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:"\\“\\%\\‘\\”\\�\\．\\⋯\\！\\－\\：\\–\\。\\》\\,\\）\\,\\？\\；\\～\\~\\…\\︰\\，\\（\\」\\‧\\《\\﹔\\、\\—\\／\\,\\「\\﹖\\·\\×\\̃\\̌\\ε\\λ\\μ\\и\\т\\─\\□\\〈\\〉\\『\\』\\ア\\オ\\カ\\チ\\ド\\ベ\\ャ\\ヤ\\ン\\・\\丶\\ａ\\ｂ\\ｆ\\ｇ\\ｉ\\ｎ\\ｐ\\ｔ' + "\\']"
 
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
@@ -145,7 +145,7 @@ result = test_dataset.map(evaluate, batched=True, batch_size=8)
 print("CER: {:2f}".format(100 * chunked_cer(predictions=result["pred_strings"], targets=result["sentence"], chunk_size=1000)))
 ```
 
-**Test Result**: 43.00 %
+**Test Result**: 41.987498 %
 
 
 ## Training