Update README.md

README.md

@@ -58,27 +58,28 @@ When using this model, make sure that your speech input is sampled at 16kHz.
 To transcribe audio files the model can be used as a standalone acoustic model as follows:
 
 ```python
- from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
- from datasets import load_dataset
- import torch
+from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
+from datasets import load_dataset
+import torch
  
- # load model and tokenizer
- processor = Wav2Vec2Processor.from_pretrained("bond005/wav2vec2-large-ru-golos")
- model = Wav2Vec2ForCTC.from_pretrained("bond005/wav2vec2-large-ru-golos")
+# load model and tokenizer
+processor = Wav2Vec2Processor.from_pretrained("bond005/wav2vec2-large-ru-golos")
+model = Wav2Vec2ForCTC.from_pretrained("bond005/wav2vec2-large-ru-golos")
      
- # load dummy dataset and read soundfiles
- ds = load_dataset("bond005/sberdevices_golos_10h_crowd", split="test")
+# load test part of Golos dataset and read first soundfile
+ds = load_dataset("bond005/sberdevices_golos_10h_crowd", split="test")
  
- # tokenize
- processed = processor(ds[0]["audio"]["array"], return_tensors="pt", padding="longest")  # Batch size 1
+# tokenize
+processed = processor(ds[0]["audio"]["array"], return_tensors="pt", padding="longest")  # Batch size 1
  
- # retrieve logits
- logits = model(processed.input_values, attention_mask=processed.attention_mask).logits
+# retrieve logits
+logits = model(processed.input_values, attention_mask=processed.attention_mask).logits
  
- # take argmax and decode
- predicted_ids = torch.argmax(logits, dim=-1)
- transcription = processor.batch_decode(predicted_ids)
- ```
+# take argmax and decode
+predicted_ids = torch.argmax(logits, dim=-1)
+transcription = processor.batch_decode(predicted_ids)[0]
+print(transcription)
+```
 
 ## Citation
 If you want to cite this model you can use this: