RuudVelo
/

wav2vec2-large-xlsr-53-frisian

Automatic Speech Recognition Transformers PyTorch JAX wav2vec2 audio speech xlsr-fine-tuning-week Eval Results Inference Endpoints

Model card Files Files and versions Community

RuudVelo commited on Mar 26, 2021

Commit

d7249dc

•

1 Parent(s): 1701ccd

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -19,7 +19,7 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 30.13
 ---
@@ -38,7 +38,7 @@ import sys
 model_name = "RuudVelo/wav2vec2-large-xlsr-53-frisian"
 device = "cuda"
-chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\â€œ\\%\\â€˜\\â€\\ï¿½]'
 model = Wav2Vec2ForCTC.from_pretrained(model_name).to(device)
 processor = Wav2Vec2Processor.from_pretrained(model_name)
@@ -73,4 +73,4 @@ wer = load_metric("wer")
 print(wer.compute(predictions=result["predicted"], references=result["target"]))
 ```
-**Result**: 30.13 %

     metrics:
        - name: Test WER
          type: wer
+         value: 20.35
 ---
 model_name = "RuudVelo/wav2vec2-large-xlsr-53-frisian"
 device = "cuda"
+chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\â€œ\\\\%\\\\â€˜\\\\â€\\\\ï¿½]'
 model = Wav2Vec2ForCTC.from_pretrained(model_name).to(device)
 processor = Wav2Vec2Processor.from_pretrained(model_name)
 print(wer.compute(predictions=result["predicted"], references=result["target"]))
 ```
+**Result**: 20.35 %