Fix examples: input_ids -> input_features (#1)

- Fix examples: input_ids -> input_features (ab7755c91c785dcd7ab71428a8f8a22c8a5cd3fa)


Co-authored-by: Sanchit Gandhi <sanchit-gandhi@users.noreply.huggingface.co>

README.md

@@ -72,7 +72,7 @@ input_features = processor(
     sampling_rate=16_000,
     return_tensors="pt"
 ).input_features  # Batch size 1
-generated_ids = model.generate(input_ids=input_features)
+generated_ids = model.generate(input_features=input_features)
 
 transcription = processor.batch_decode(generated_ids)
 ```
@@ -83,35 +83,29 @@ The following script shows how to evaluate this model on the [LibriSpeech](https
 *"clean"* and *"other"* test dataset.
 
 ```python
-from datasets import load_dataset, load_metric
+from datasets import load_dataset
+from evaluate import load
 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")
+wer = load("wer")
 
 model = Speech2TextForConditionalGeneration.from_pretrained("facebook/s2t-medium-librispeech-asr").to("cuda")
 processor = Speech2TextProcessor.from_pretrained("facebook/s2t-medium-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")
 
-    gen_tokens = model.generate(input_ids=input_features, attention_mask=attention_mask)
-    batch["transcription"] = processor.batch_decode(gen_tokens, skip_special_tokens=True)
+    gen_tokens = model.generate(input_features=input_features, attention_mask=attention_mask)
+    batch["transcription"] = processor.batch_decode(gen_tokens, skip_special_tokens=True)[0]
     return batch
 
-result = librispeech_eval.map(map_to_pred, batched=True, batch_size=8, remove_columns=["speech"])
+result = librispeech_eval.map(map_to_pred, remove_columns=["audio"])
 
-print("WER:", wer(predictions=result["transcription"], references=result["text"]))
+print("WER:", wer.compute(predictions=result["transcription"], references=result["text"]))
 ```
 
 *Result (WER)*: