anuragshas
/

wav2vec2-large-xlsr-as

Automatic Speech Recognition

xlsr-fine-tuning-week

Model card Files Files and versions

anuragshas commited on Jan 14, 2022

Commit

d694748

·

1 Parent(s): 9d091ef

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -73,7 +73,7 @@ resampler = torchaudio.transforms.Resample(48_000, 16_000)
 def speech_file_to_array_fn(batch):
     batch["sentence"] = re.sub('’ ',' ',batch["sentence"])
     batch["sentence"] = re.sub(' ‘',' ',batch["sentence"])
-    batch["sentence"] = re.sub('’|‘','\\'',batch["sentence"])
     batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
     speech_array, sampling_rate = torchaudio.load(batch["path"])
     batch["speech"] = resampler(speech_array).squeeze().numpy()

 def speech_file_to_array_fn(batch):
     batch["sentence"] = re.sub('’ ',' ',batch["sentence"])
     batch["sentence"] = re.sub(' ‘',' ',batch["sentence"])
+    batch["sentence"] = re.sub('’|‘','\'',batch["sentence"])
     batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
     speech_array, sampling_rate = torchaudio.load(batch["path"])
     batch["speech"] = resampler(speech_array).squeeze().numpy()