Update README.md

README.md

@@ -1,5 +1,5 @@
 ---
-language: {el} 
+language: el 
 datasets:
 - common_voice 
 metrics:
@@ -11,24 +11,24 @@ tags:
 - xlsr-fine-tuning-week
 license: apache-2.0
 model-index:
-- name: {Greek XLSR Wav2Vec2 Large 53} 
+- name: Greek XLSR Wav2Vec2 Large 53
 results:
 - task: 
     name: Speech Recognition
     type: automatic-speech-recognition
     dataset:
-      name: Common Voice {el}
+      name: Common Voice el
       type: common_voice
-      args: {el} 
+      args: el 
     metrics:
        - name: Test WER
          type: wer
-         value: {1.00} 
+         value: ???
 ---
 
 # Wav2Vec2-Large-XLSR-53-{Greek} 
 
-Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on {Greek} using the [Common Voice](https://huggingface.co/datasets/common_voice), ... and ... dataset{s}. #TODO: replace {language} with your language, *e.g.* French and eventually add more datasets that were used and eventually remove common voice if model was not trained on common voice
+Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Greek using the [Common Voice](https://huggingface.co/datasets/common_voice), ... and ... dataset{s}. #TODO: replace {language} with your language, *e.g.* French and eventually add more datasets that were used and eventually remove common voice if model was not trained on common voice
 When using this model, make sure that your speech input is sampled at 16kHz.
 
 ## Usage
@@ -41,19 +41,19 @@ import torchaudio
 from datasets import load_dataset
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 test_dataset = load_dataset("common_voice", "{el}", split="test[:2%]") #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.
-processor = Wav2Vec2Processor.from_pretrained("{skylord/greek_lsr_1}") #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("{skylord/greek_lsr_1}") #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("skylord/greek_lsr_1") 
+model = Wav2Vec2ForCTC.from_pretrained("skylord/greek_lsr_1") 
 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"])
+\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
+\treturn 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
+\tlogits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
 predicted_ids = torch.argmax(logits, dim=-1)
 print("Prediction:", processor.batch_decode(predicted_ids))
 print("Reference:", test_dataset["sentence"][:2])
@@ -62,7 +62,7 @@ print("Reference:", test_dataset["sentence"][:2])
 
 ## Evaluation
 
-The model can be evaluated as follows on the {Greek} 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 Greek test data of Common Voice. 
 
 
 ```python
@@ -71,35 +71,35 @@ import torchaudio
 from datasets import load_dataset, load_metric
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 import re
-test_dataset = load_dataset("common_voice", "{el}", 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", "el", split="test") 
 wer = load_metric("wer")
-processor = Wav2Vec2Processor.from_pretrained("{skylord/greek_lsr_1}") #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("{skylord/greek_lsr_1}") #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("skylord/greek_lsr_}") 
+model = Wav2Vec2ForCTC.from_pretrained("skylord/greek_lsr_1")
 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 = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“]'  # TODO: adapt this list to include all special characters you removed from the data
 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
+\tbatch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
+\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
+\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
+\treturn 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)
-	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
+\tinputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
+\twith torch.no_grad():
+\t\tlogits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
+\tpred_ids = torch.argmax(logits, dim=-1)
+\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
+\treturn 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**: 1.00 %  # 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**: 1.00 % 
 
 
 ## Training