Update README.md

README.md

@@ -47,13 +47,13 @@ test_dataset = load_dataset("common_voice", "fi", split="test[:2%]")
 processor = Wav2Vec2Processor.from_pretrained("aapot/wav2vec2-large-xlsr-53-finnish")
 model = Wav2Vec2ForCTC.from_pretrained("aapot/wav2vec2-large-xlsr-53-finnish")
 
-resampler = lambda sr, y: librosa.resample(y.squeeze(), sr, 16_000)
+resampler = lambda sr, y: librosa.resample(y.numpy().squeeze(), sr, 16_000)
 
 # Preprocessing the datasets.
 # We need to read the audio files as arrays
 def speech_file_to_array_fn(batch):
     speech_array, sampling_rate = torchaudio.load(batch["path"])
-    batch["speech"] = resampler(sampling_rate, speech_array.numpy()).squeeze()
+    batch["speech"] = resampler(sampling_rate, speech_array).squeeze()
     return batch
 
 test_dataset = test_dataset.map(speech_file_to_array_fn)
@@ -90,14 +90,14 @@ model = Wav2Vec2ForCTC.from_pretrained("aapot/wav2vec2-large-xlsr-53-finnish")
 model.to("cuda")
 
 chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�\'\...\…\–\é]'
-resampler = lambda sr: lambda y: librosa.resample(y.numpy().squeeze(), sr, 16_000)
+resampler = lambda sr, y: librosa.resample(y.numpy().squeeze(), sr, 16_000)
 
 # Preprocessing the datasets.
 # We need to read the audio files as arrays
 def speech_file_to_array_fn(batch):
   batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
   speech_array, sampling_rate = torchaudio.load(batch["path"])
-  batch["speech"] = resampler(sampling_rate)(speech_array).squeeze()
+  batch["speech"] = resampler(sampling_rate, speech_array).squeeze()
   return batch
 
 test_dataset = test_dataset.map(speech_file_to_array_fn)