Update README.md

README.md

@@ -6,6 +6,11 @@ tags:
 - speech
 - audio
 - automatic-speech-recognition
+widget:
+- label: Librispeech sample 1
+  src: https://cdn-media.huggingface.co/speech_samples/sample1.flac
+- label: Librispeech sample 2
+  src: https://cdn-media.huggingface.co/speech_samples/sample2.flac
 license: apache-2.0
 ---
 
@@ -59,52 +64,4 @@ 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 = processor.batch_decode(predicted_ids)
- ```
- 
-  ## Evaluation
- 
- This code snippet shows how to evaluate **facebook/wav2vec2-large-960h-lv60-self** on LibriSpeech's "clean" and "other" test data.
- 
-```python
-from datasets import load_dataset
-from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
-import soundfile as sf
-import torch
-from jiwer import wer
-
-
-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")
-    input_values = inputs.input_values.to("cuda")
-    attention_mask = inputs.attention_mask.to("cuda")
-    
-    with torch.no_grad():
-        logits = model(input_values, attention_mask=attention_mask).logits
-
-    predicted_ids = torch.argmax(logits, dim=-1)
-    transcription = processor.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"]))
-```
-
-*Result (WER)*:
-
-| "clean" | "other" |
-|---|---|
-| 1.9 | 3.9 |
+ ```