Update README.md

README.md

@@ -56,7 +56,7 @@ def speech_file_to_array_fn(batch):
     return batch
 
 test_dataset = test_dataset.map(speech_file_to_array_fn)
-inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True)
+inputs = processor(test_dataset[:2]["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
 
 with torch.no_grad():
     logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
@@ -64,7 +64,7 @@ with torch.no_grad():
 predicted_ids = torch.argmax(logits, dim=-1)
 
 print("Prediction:", processor.batch_decode(predicted_ids))
-print("Reference:", test_dataset["sentence"][:2])
+print("Reference:", test_dataset[:2]["sentence"])
 ```
 
 
@@ -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)