update README

README.md

@@ -24,11 +24,10 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 13.32
+         value: 11.85
        - name: Test CER
          type: cer
-         value: 3.71
-
+         value: 3.17
 ---
 
 # Wav2Vec2-Large-XLSR-53-German
@@ -102,15 +101,12 @@ from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 LANG_ID = "de"
 MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-german"
 DEVICE = "cuda"
-MAX_SAMPLES = 8000
 
 CHARS_TO_IGNORE = [",", "?", "¿", ".", "!", "¡", ";", ":", '""', "%", '"', "�", "ʿ", "·", "჻", "~", "՞", 
                    "؟", "،", "।", "॥", "«", "»", "„", "“", "”", "「", "」", "‘", "’", "《", "》", "(", ")", "[", "]",
                    "=", "`", "_", "+", "<", ">", "…", "–", "°", "´", "ʾ", "‹", "›", "©", "®", "—", "→", "。"]
 
 test_dataset = load_dataset("common_voice", LANG_ID, split="test")
-if len(test_dataset) > MAX_SAMPLES:
-    test_dataset = test_dataset.select(range(MAX_SAMPLES))
 
 wer = load_metric("wer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/wer.py
 cer = load_metric("cer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/cer.py
@@ -153,5 +149,5 @@ print("CER: {:2f}".format(100 * cer.compute(predictions=result["pred_strings"],
 
 **Test Result**:
 
-- WER: 13.32%
-- CER: 3.71%
+- WER: 11.85%
+- CER: 3.17%