Update README.md

README.md

@@ -69,25 +69,18 @@ with `pip install torchaudio sentencepiece`.
 import torch
 from transformers import Speech2TextProcessor, Speech2TextForConditionalGeneration
 from datasets import load_dataset
-import soundfile as sf
 
 model = Speech2TextForConditionalGeneration.from_pretrained("facebook/s2t-small-librispeech-asr")
 processor = Speech2TextProcessor.from_pretrained("facebook/s2t-small-librispeech-asr")
 
-def map_to_array(batch):
-    speech, _ = sf.read(batch["file"])
-    batch["speech"] = speech
-    return batch
-
 ds = load_dataset(
     "patrickvonplaten/librispeech_asr_dummy",
     "clean",
     split="validation"
 )
-ds = ds.map(map_to_array)
 
 input_features = processor(
-    ds["speech"][0],
+    ds["audio"]["array"][0],
     sampling_rate=16_000,
     return_tensors="pt"
 ).input_features  # Batch size 1
@@ -104,7 +97,6 @@ The following script shows how to evaluate this model on the [LibriSpeech](https
 ```python
 from datasets import load_dataset, load_metric
 from transformers import Speech2TextForConditionalGeneration, Speech2TextProcessor
-import soundfile as sf
 
 librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")  # change to "other" for other test dataset
 wer = load_metric("wer")
@@ -112,15 +104,10 @@ wer = load_metric("wer")
 model = Speech2TextForConditionalGeneration.from_pretrained("facebook/s2t-small-librispeech-asr").to("cuda")
 processor = Speech2TextProcessor.from_pretrained("facebook/s2t-small-librispeech-asr", do_upper_case=True)
 
-def map_to_array(batch):
-    speech, _ = sf.read(batch["file"])
-    batch["speech"] = speech
-    return batch
-
 librispeech_eval = librispeech_eval.map(map_to_array)
 
 def map_to_pred(batch):
-    features = processor(batch["speech"], sampling_rate=16000, padding=True, return_tensors="pt")
+    features = processor(batch["audio"]["array"], sampling_rate=16000, padding=True, return_tensors="pt")
     input_features = features.input_features.to("cuda")
     attention_mask = features.attention_mask.to("cuda")