iarfmoose
/

wav2vec2-large-xlsr-frisian

Automatic Speech Recognition

xlsr-fine-tuning-week

Inference Endpoints

Model card Files Files and versions Community

patrickvonplaten commited on Mar 29, 2021

Commit

c0e2844

•

1 Parent(s): 5b8770d

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -17,7 +17,7 @@ model-index:
     dataset:
       name: Common Voice fy-NL
       type: common_voice
-      args: {lang_id}
     metrics:
        - name: Test WER
          type: wer
@@ -84,7 +84,7 @@ processor = Wav2Vec2Processor.from_pretrained("iarfmoose/wav2vec2-large-xlsr-fri
 model = Wav2Vec2ForCTC.from_pretrained("iarfmoose/wav2vec2-large-xlsr-frisian")
 model.to("cuda")
-chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�\–\—\¬\⅛]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 def speech_file_to_array_fn(batch):

     dataset:
       name: Common Voice fy-NL
       type: common_voice
+      args: fy-NL
     metrics:
        - name: Test WER
          type: wer
 model = Wav2Vec2ForCTC.from_pretrained("iarfmoose/wav2vec2-large-xlsr-frisian")
 model.to("cuda")
+chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”\\�\\–\\—\\¬\\⅛]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 def speech_file_to_array_fn(batch):