Update README.md

README.md

@@ -10,7 +10,7 @@ tags:
 - speech
 license: apache-2.0
 model-index:
-- name: Wav2Vec2 Luganda
+- name: Wav2Vec2 Luganda by Indonesian-NLP
   results:
   - task: 
       name: Speech Recognition
@@ -54,7 +54,10 @@ resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.
 # We need to read the aduio files as arrays
 def speech_file_to_array_fn(batch):
-    speech_array, sampling_rate = torchaudio.load(batch["path"])
+    if "audio" in batch:
+        speech_array = torch.tensor(batch["audio"]["array"])
+    else:
+        speech_array, sampling_rate = torchaudio.load(batch["path"])
     batch["speech"] = resampler(speech_array).squeeze().numpy()
     return batch
 
@@ -98,7 +101,10 @@ resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # 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"])
+    if "audio" in batch:
+        speech_array = torch.tensor(batch["audio"]["array"])
+    else:
+        speech_array, sampling_rate = torchaudio.load(batch["path"])
     batch["speech"] = resampler(speech_array).squeeze().numpy()
     return batch