Update README.md

README.md

@@ -51,21 +51,24 @@ python eval.py --model_id kingabzpro/wav2vec2-large-xls-r-300m-Urdu --dataset mo
 ### Inference With LM
 
 ```python
-import torch
-from datasets import load_dataset
-from transformers import AutoModelForCTC, AutoProcessor
-import torchaudio.functional as F
-model_id = "kingabzpro/wav2vec2-large-xls-r-300m-Urdu"
-sample_iter = iter(load_dataset("mozilla-foundation/common_voice_8_0", "ur", split="test", streaming=True, use_auth_token=True))
+from datasets import load_dataset, Audio
+from transformers import pipeline
+model = "kingabzpro/wav2vec2-large-xls-r-300m-Urdu"
+data = load_dataset("mozilla-foundation/common_voice_8_0",
+                     "ur",
+                     split="test", 
+                     streaming=True, 
+                     use_auth_token=True)
+
+sample_iter = iter(data.cast_column("path", Audio(sampling_rate=16_000)))
 sample = next(sample_iter)
-resampled_audio = F.resample(torch.tensor(sample["audio"]["array"]), 48_000, 16_000).numpy()
-model = AutoModelForCTC.from_pretrained(model_id)
-processor = AutoProcessor.from_pretrained(model_id)
-input_values = processor(resampled_audio, return_tensors="pt").input_values
-with torch.no_grad():
-    logits = model(input_values).logits
-transcription = processor.batch_decode(logits.numpy()).text
-# => "اب نے ٹپیدسون دیتے ہیں"
+
+asr = pipeline("automatic-speech-recognition", model=model)
+prediction = asr(sample["path"]["array"], 
+                  chunk_length_s=5, 
+                  stride_length_s=1)
+prediction
+# => {'text': 'اب یہ ونگین لمحاتانکھار دلمیں میںفوث کریلیا اجائ'}
 ```