t

app.py

@@ -76,12 +76,12 @@ with gr.Blocks() as app:
             with gr.Group():
                 with gr.Row():
                     transcript_ugArab_box = gr.Textbox(
-                        label="User Transcript (Arabic Script)",
+                        label="User Pronunciation Transcript (Arabic Script)",
                         placeholder="ASR transcription of user audio..."
                     )
                 with gr.Row():
                     transcript_ugLatn_box = gr.Textbox(
-                        label="User Transcript (Latin Script)",
+                        label="User Pronunciation Transcript (Latin Script)",
                         placeholder="ASR transcription of user audio..."
                     )
             # IPA

asr.py

@@ -33,7 +33,7 @@ def asr(audio_data, target_rate = 16000):
         sampling_rate = target_rate
     
     # Process audio through ASR model
-    inputs = asr_processor(audio_input.squeeze(), sampling_rate=sampling_rate, return_tensors="pt", padding=True)
+    inputs = asr_processor(audio_input.squeeze(), sampling_rate=sampling_rate, return_tensors="pt")
     inputs = {key: val.to(device) for key, val in inputs.items()}
     with torch.no_grad():
         logits = asr_model(**inputs).logits