Update README.md

README.md

@@ -33,6 +33,38 @@ transcription = processor.batch_decode(predicted_ids)
 print("HF prediction: ", transcription)
 ```
 
+
+This code snipnet shows how to Evaluate the wav2vec2-xlsr-300m-quechua in [Second Americas NLP 2022 Quechua dev set](https://huggingface.co/datasets/ivangtorre/second_americas_nlp_2022)
+
+```python
+from datasets import load_dataset
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+import torch
+from jiwer import cer
+import torch.nn.functional as F
+
+
+#librispeech_eval = load_dataset("ivangtorre/second_americas_nlp_2022", split="validation")
+librispeech_eval = load_dataset("ivangtorre/second_americas_nlp_2022", split="validation")
+
+model = Wav2Vec2ForCTC.from_pretrained("ivangtorre/wav2vec2-xlsr-300m-quechua")
+processor = Wav2Vec2Processor.from_pretrained("ivangtorre/wav2vec2-xlsr-300m-quechua")
+
+def map_to_pred(batch):
+    wav = batch["audio"][0]["array"]
+    feats = torch.from_numpy(wav).float()
+    feats = F.layer_norm(feats, feats.shape) # Normalization performed during finetuning
+    feats = torch.unsqueeze(feats, 0)
+    logits = model(feats).logits
+    predicted_ids = torch.argmax(logits, dim=-1)
+    batch["transcription"] = processor.batch_decode(predicted_ids)
+    return batch
+
+result = librispeech_eval.map(map_to_pred, batched=True, batch_size=1)
+
+print("CER:", cer(result["source_processed"], result["transcription"]))
+```
+
 ## Citation
 
 ```bibtex