Update README.md

README.md

@@ -48,25 +48,17 @@ To transcribe audio files the model can be used as a standalone acoustic model a
 ```python
  from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
  from datasets import load_dataset
- import soundfile as sf
  import torch
  
  # load model and processor
  processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-large-960h-lv60-self")
  model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-large-960h-lv60-self")
- 
- # define function to read in sound file
- def map_to_array(batch):
-     speech, _ = sf.read(batch["file"])
-     batch["speech"] = speech
-     return batch
      
  # load dummy dataset and read soundfiles
  ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
- ds = ds.map(map_to_array)
  
  # tokenize
- input_values = processor(ds["speech"][:2], return_tensors="pt", padding="longest").input_values  # Batch size 1
+ input_values = processor(batch["audio"]["array"], return_tensors="pt", padding="longest").input_values
  
  # retrieve logits
  logits = model(input_values).logits
@@ -83,7 +75,6 @@ To transcribe audio files the model can be used as a standalone acoustic model a
 ```python
 from datasets import load_dataset
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
-import soundfile as sf
 import torch
 from jiwer import wer
 
@@ -93,15 +84,8 @@ librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")
 model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-large-960h-lv60-self").to("cuda")
 processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-large-960h-lv60-self")
 
-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):
-    inputs = processor(batch["speech"], return_tensors="pt", padding="longest")
+    inputs = processor(batch["audio"]["array"], return_tensors="pt", padding="longest")
     input_values = inputs.input_values.to("cuda")
     attention_mask = inputs.attention_mask.to("cuda")
     
@@ -113,7 +97,7 @@ def map_to_pred(batch):
     batch["transcription"] = transcription
     return batch
 
-result = librispeech_eval.map(map_to_pred, batched=True, batch_size=16, remove_columns=["speech"])
+result = librispeech_eval.map(map_to_pred, remove_columns=["speech"])
 
 print("WER:", wer(result["text"], result["transcription"]))
 ```