Update README.md

README.md

@@ -51,15 +51,15 @@ 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):
-	speech_array, sampling_rate = torchaudio.load(batch["path"])
-	batch["speech"] = resampler(speech_array).squeeze().numpy()
-	return batch
+    speech_array, sampling_rate = torchaudio.load(batch["path"])
+    batch["speech"] = resampler(speech_array).squeeze().numpy()
+    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)
 
 with torch.no_grad():
-	logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
+    logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
 
 predicted_ids = torch.argmax(logits, dim=-1)
 
@@ -70,58 +70,62 @@ print("Reference:", test_dataset["sentence"][:2])
 
 ## Evaluation
 
-The model can be evaluated as follows on the {language} test data of Common Voice.  # TODO: replace #TODO: replace language with your {language}, *e.g.* French
-
+The model can be evaluated as follows on the zh-CN test data of Common Voice.
+Original CER calculation refer to https://huggingface.co/ctl/wav2vec2-large-xlsr-cantonese
 
 ```python
+!mkdir cer
+!wget -O cer/cer.py https://huggingface.co/ctl/wav2vec2-large-xlsr-cantonese/raw/main/cer.py
+!pip install jiwer
+
 import torch
 import torchaudio
 from datasets import load_dataset, load_metric
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 import re
 
-test_dataset = load_dataset("common_voice", "{lang_id}", split="test") #TODO: replace {lang_id} in your language code here. Make sure the code is one of the *ISO codes* of [this](https://huggingface.co/languages) site.
+test_dataset = load_dataset("common_voice", "zh-CN", split="test")
 wer = load_metric("wer")
 
-processor = Wav2Vec2Processor.from_pretrained("{model_id}") #TODO: replace {model_id} with your model id. The model id consists of {your_username}/{your_modelname}, *e.g.* `elgeish/wav2vec2-large-xlsr-53-arabic`
-model = Wav2Vec2ForCTC.from_pretrained("{model_id}") #TODO: replace {model_id} with your model id. The model id consists of {your_username}/{your_modelname}, *e.g.* `elgeish/wav2vec2-large-xlsr-53-arabic`
+processor = Wav2Vec2Processor.from_pretrained("ydshieh/wav2vec2-large-xlsr-53-chinese-zh-cn-gpt")
+model = Wav2Vec2ForCTC.from_pretrained("ydshieh/wav2vec2-large-xlsr-53-chinese-zh-cn-gpt")
 model.to("cuda")
 
-chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“]'  # TODO: adapt this list to include all special characters you removed from the data
+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)
 
 # Preprocessing the datasets.
 # We need to read the aduio files as arrays
 def speech_file_to_array_fn(batch):
-	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()
-	return batch
+    batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower().replace("’", "'") + " "
+    speech_array, sampling_rate = torchaudio.load(batch["path"])
+    batch["speech"] = resampler(speech_array).squeeze().numpy()
+    return batch
 
 test_dataset = test_dataset.map(speech_file_to_array_fn)
 
 # Preprocessing the datasets.
 # We need to read the aduio files as arrays
 def evaluate(batch):
-	inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
+    inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
 
-	with torch.no_grad():
-		logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
+    with torch.no_grad():
+        logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
 
-	pred_ids = torch.argmax(logits, dim=-1)
-	batch["pred_strings"] = processor.batch_decode(pred_ids)
-	return batch
+    pred_ids = torch.argmax(logits, dim=-1)
+    batch["pred_strings"] = processor.batch_decode(pred_ids)
+    return 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**: XX.XX %  # TODO: write output of print here. IMPORTANT: Please remember to also replace {wer_result_on_test} at the top of with this value here. tags.
+**Test Result**: 43.00 %
 
 
 ## Training
 
-The Common Voice `train`, `validation`, and ... datasets were used for training as well as ... and ...  # TODO: adapt to state all the datasets that were used for training.
+The Common Voice zh-CN `train`, `validation` were used for training, as well as Common Voice zh-TW `train`, `validation` and `test` datasets.
 
-The script used for training can be found [here](...) # TODO: fill in a link to your training script here. If you trained your model in a colab, simply fill in the link here. If you trained the model locally, it would be great if you could upload the training script on github and paste the link here.
+The script used for training can be found [to be uploaded later](...)