Update README.md

README.md

@@ -60,4 +60,47 @@ To transcribe audio files the model can be used as a standalone acoustic model a
  # take argmax and decode
  predicted_ids = torch.argmax(logits, dim=-1)
  transcription = tokenizer.batch_decode(predicted_ids)
- ```
+ ```
+ 
+ ## Evalution
+ 
+ This is a short script to show how the dataset can be evaluated on librispeech "clean" and "other" test data.
+ 
+```python
+from datasets import load_dataset
+from transformers import Wav2Vec2ForMaskedLM, Wav2Vec2Tokenizer
+import soundfile as sf
+import torch
+from jiwer import wer
+
+
+librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")
+
+model = Wav2Vec2ForMaskedLM.from_pretrained("facebook/wav2vec2-base-960h").to("cuda")
+tokenizer = Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-base-960h")
+
+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):
+    input_values = tokenizer(batch["speech"], return_tensors="pt", padding="longest").input_values
+    with torch.no_grad():
+        logits = model(input_values.to("cuda")).logits
+
+    predicted_ids = torch.argmax(logits, dim=-1)
+    transcription = tokenizer.batch_decode(predicted_ids)
+    batch["transcription"] = transcription
+    return batch
+
+result = librispeech_eval.map(map_to_pred, batched=True, batch_size=16, remove_columns=["speech"])
+
+print("WER:", wer(result["text"], result["transcription"]))
+```
+
+| "clean" | "other" |
+|---|---|
+| 4.1 |   |