Update app.py

app.py

@@ -1,30 +1,21 @@
 import gradio as gr
 import torch
 import librosa
-from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
+from transformers import pipeline
 
-# Load model
-processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h")
-model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h")
+# Use pipeline instead (lighter + safer)
+pipe = pipeline("automatic-speech-recognition", model="facebook/wav2vec2-base-960h")
 
 def transcribe(audio):
     audio, sr = librosa.load(audio, sr=16000)
-    inputs = processor(audio, sampling_rate=16000, return_tensors="pt", padding=True)
+    result = pipe(audio)
+    return result["text"]
 
-    with torch.no_grad():
-        logits = model(inputs.input_values).logits
-
-    predicted_ids = torch.argmax(logits, dim=-1)
-    transcription = processor.batch_decode(predicted_ids)[0]
-
-    return transcription
-
-interface = gr.Interface(
+iface = gr.Interface(
     fn=transcribe,
     inputs=gr.Audio(type="filepath"),
     outputs="text",
     title="Speech to Text",
-    description="Upload audio file and get transcription"
 )
 
-interface.launch()
+iface.launch()