Update README.md

README.md

@@ -73,9 +73,11 @@ from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 import torch
 from jiwer import cer
 import torch.nn.functional as F
+from datasets import load_dataset
+import soundfile as sf
 
-
-librispeech_eval = load_dataset("ivangtorre/second_americas_nlp_2022", split="validation")
+americasnlp = load_dataset("ivangtorre/second_americas_nlp_2022", "quechua", split="dev")
+quechua = americasnlp.filter(lambda language: language['subset']=='quechua')
 
 model = Wav2Vec2ForCTC.from_pretrained("ivangtorre/wav2vec2-xlsr-300m-quechua")
 processor = Wav2Vec2Processor.from_pretrained("ivangtorre/wav2vec2-xlsr-300m-quechua")
@@ -90,7 +92,7 @@ def map_to_pred(batch):
     batch["transcription"] = processor.batch_decode(predicted_ids)
     return batch
 
-result = librispeech_eval.map(map_to_pred, batched=True, batch_size=1)
+result = quechua.map(map_to_pred, batched=True, batch_size=1)
 
 print("CER:", cer(result["source_processed"], result["transcription"]))
 ```