cpierse
/

wav2vec2-large-xlsr-53-esperanto

Automatic Speech Recognition Transformers PyTorch JAX Safetensors

Esperanto wav2vec2 audio speech xlsr-fine-tuning-week Eval Results Inference Endpoints

Model card Files Files and versions Community

cpierse commited on Mar 28, 2021

Commit

61264b6

•

1 Parent(s): 368bea4

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -23,7 +23,7 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value:  12.31
 ---
 # Wav2Vec2-Large-XLSR-53-eo
@@ -103,7 +103,7 @@ processor = Wav2Vec2Processor.from_pretrained("cpierse/wav2vec2-large-xlsr-53-es
 model = Wav2Vec2ForCTC.from_pretrained("cpierse/wav2vec2-large-xlsr-53-esperanto")
 model.to("cuda")
-chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”\\�\\„\\«\\(\\»\\)\\’\\']'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.

     metrics:
        - name: Test WER
          type: wer
+         value: 12.31
 ---
 # Wav2Vec2-Large-XLSR-53-eo
 model = Wav2Vec2ForCTC.from_pretrained("cpierse/wav2vec2-large-xlsr-53-esperanto")
 model.to("cuda")
+chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“\\\\%\\\\‘\\\\”\\\\�\\\\„\\\\«\\\\(\\\\»\\\\)\\\\’\\\\']'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.