Pure python evaluation

README.md

@@ -80,11 +80,19 @@ tar -zxvf cv.tar.gz
 ```python
 import torch
 import torchaudio
+import urllib.request
+import tarfile
 import pandas as pd
 from tqdm.auto import tqdm
-from datasets import load_dataset, load_metric
+from datasets import load_metric
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 
+# Download the raw data instead of using HF datasets to save space 
+data_url = "https://voice-prod-bundler-ee1969a6ce8178826482b88e843c335139bd3fb4.s3.amazonaws.com/cv-corpus-6.1-2020-12-11/cv.tar.gz"
+filestream = urllib.request.urlopen(data_url)
+data_file = tarfile.open(fileobj=filestream, mode="r|gz")
+data_file.extractall()
+
 wer = load_metric("wer")
 
 processor = Wav2Vec2Processor.from_pretrained("anton-l/wav2vec2-large-xlsr-53-chuvash")
@@ -97,7 +105,7 @@ clips_path = "cv-corpus-6.1-2020-12-11/cv/clips/"
 def clean_sentence(sent):
     sent = sent.lower()
     # replace non-alpha characters with space
-    sent = "".join(ch if ch.isalpha() or ch == "'" else " " for ch in sent)
+    sent = "".join(ch if ch.isalpha() else " " for ch in sent)
     # remove repeated spaces
     sent = " ".join(sent.split())
     return sent