gchhablani
/

wav2vec2-large-xlsr-eo

Automatic Speech Recognition Transformers PyTorch JAX

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

Model card Files Files and versions Community

patrickvonplaten commited on Mar 30, 2021

Commit

e0e341d

•

1 Parent(s): fe5c991

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -23,7 +23,7 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 9.92
 ---
 # Wav2Vec2-Large-XLSR-53-Esperanto
@@ -105,7 +105,7 @@ processor = Wav2Vec2Processor.from_pretrained('gchhablani/wav2vec2-large-xlsr-eo
 model = Wav2Vec2ForCTC.from_pretrained('gchhablani/wav2vec2-large-xlsr-eo')
 model.to("cuda")
-chars_to_ignore_regex = """[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“\\\\%\\\\‘\\\\”\\\\�\\\\„\\\\«\\\\(\\\\»\\\\)\\\\’\\\\']"""
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.
@@ -135,7 +135,7 @@ result = test_dataset.map(evaluate, batched=True, batch_size=8)
 print("WER: {:2f}".format(100 * chunked_wer(predictions=result["pred_strings"], targets=result["sentence"],chunk_size=5000)))
 ```
-**Test Result**: 9.92 %
 ## Training

     metrics:
        - name: Test WER
          type: wer
+         value: 10.13
 ---
 # Wav2Vec2-Large-XLSR-53-Esperanto
 model = Wav2Vec2ForCTC.from_pretrained('gchhablani/wav2vec2-large-xlsr-eo')
 model.to("cuda")
+chars_to_ignore_regex = """[\\\\\\\\,\\\\\\\\?\\\\\\\\.\\\\\\\\!\\\\\\\\-\\\\\\\\;\\\\\\\\:\\\\\\\\"\\\\\\\\“\\\\\\\\%\\\\\\\\‘\\\\\\\\”\\\\\\\\�\\\\\\\\„\\\\\\\\«\\\\\\\\(\\\\\\\\»\\\\\\\\)\\\\\\\\’\\\\\\\\']"""
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.
 print("WER: {:2f}".format(100 * chunked_wer(predictions=result["pred_strings"], targets=result["sentence"],chunk_size=5000)))
 ```
+**Test Result**: 10.13 %
 ## Training