Update README.md

README.md

@@ -31,65 +31,21 @@ model-index:
 This a the demonstration of a fine-tuned Wav2vec model for Portuguese using the following  [CORAA dataset](https://github.com/nilc-nlp/CORAA)
 
 
-## Imports and dependencies
 
+# Use this model
 
 ```python
-%%capture
-!pip install datasets
-!pip install jiwer
-!pip install torchaudio
-!pip install transformers
-!pip install soundfile
-```
-
-
-```python
-import torchaudio
-from datasets import load_dataset, load_metric
-from transformers import (
-    Wav2Vec2ForCTC,
-    Wav2Vec2Processor,
-)
-import torch
-import re
-import sys
-```
-
-## Preparation
-
-
-```python
-chars_to_ignore_regex = '[\,\?\.\!\;\:\"]'  # noqa: W605
-wer = load_metric("wer")
-device = "cuda"
-```
 
-```python
-model_name = 'Edresson/wav2vec2-large-xlsr-coraa-portuguese'
-model = Wav2Vec2ForCTC.from_pretrained(model_name).to(device)
-processor = Wav2Vec2Processor.from_pretrained(model_name)
-```
+from transformers import AutoTokenizer, Wav2Vec2ForCTC
+  
+tokenizer = AutoTokenizer.from_pretrained("Edresson/wav2vec2-large-xlsr-coraa-portuguese")
 
-```python
-def map_to_pred(batch):
-    features = processor(batch["speech"], sampling_rate=batch["sampling_rate"][0], padding=True, return_tensors="pt")
-    input_values = features.input_values.to(device)
-    attention_mask = features.attention_mask.to(device)
-    with torch.no_grad():
-        logits = model(input_values, attention_mask=attention_mask).logits
-    pred_ids = torch.argmax(logits, dim=-1)
-    batch["predicted"] = processor.batch_decode(pred_ids)
-    batch["predicted"] = [pred.lower() for pred in batch["predicted"]]
-    batch["target"] = batch["sentence"]
-    return batch
+model = Wav2Vec2ForCTC.from_pretrained("Edresson/wav2vec2-large-xlsr-coraa-portuguese")
 ```
-
-## Tests
-
+# Results
 For the results consult the [CORAA article](https://arxiv.org/abs/2110.15731)
 
-### Example with Common Voice
+# Example test with Common Voice Dataset
 
 
 ```python