Update README.md

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 68.20
+         value: 69.63
 ---
 # Wav2Vec2-Large-XLSR-53-Assamese
 Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Assamese using the [Common Voice](https://huggingface.co/datasets/common_voice).
@@ -66,14 +66,14 @@ wer = load_metric("wer")
 processor = Wav2Vec2Processor.from_pretrained("anuragshas/wav2vec2-large-xlsr-as")
 model = Wav2Vec2ForCTC.from_pretrained("anuragshas/wav2vec2-large-xlsr-as")
 model.to("cuda")
-chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\”\়\।]'
+chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\”\\়\\।]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.
 # We need to read the aduio files as arrays
 def speech_file_to_array_fn(batch):
     batch["sentence"] = re.sub('’ ',' ',batch["sentence"])
     batch["sentence"] = re.sub(' ‘',' ',batch["sentence"])
-    batch["sentence"] = re.sub('’|‘','\'',batch["sentence"])
+    batch["sentence"] = re.sub('’|‘','\\'',batch["sentence"])
     batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
     speech_array, sampling_rate = torchaudio.load(batch["path"])
     batch["speech"] = resampler(speech_array).squeeze().numpy()
@@ -91,6 +91,6 @@ def evaluate(batch):
 result = test_dataset.map(evaluate, batched=True, batch_size=8)
 print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
 ```
-**Test Result**: 68.20 % 
+**Test Result**: 69.63 % 
 ## Training
 The Common Voice `train` and `validation` datasets were used for training.