Update 3 app.py

app.py

@@ -1,23 +1,47 @@
 import gradio as gr
 import torch
-from speechbrain.pretrained import EncoderASR
 import torchaudio
+from speechbrain.pretrained import EncoderASR
 
-# Charger le modèle
-asr_model = EncoderASR.from_hparams(source="speechbrain/asr-wav2vec2-dvoice-darija", savedir="tmp_model")
+# Load the model
+try:
+    asr_model = EncoderASR.from_hparams(
+        source="speechbrain/asr-wav2vec2-dvoice-darija",
+        savedir="tmp_model",
+        run_opts={"device": "cpu"}  # Ensure compatibility with CPU if needed
+    )
+except Exception as e:
+    print(f"Error loading model: {str(e)}")
 
 def transcribe(audio):
-    waveform, sample_rate = torchaudio.load(audio)
-    transcription = asr_model.transcribe_batch(waveform)
-    return transcription[0]
+    """Transcribe audio to text using SpeechBrain ASR model."""
+    if audio is None:
+        return "No audio file uploaded. Please upload a valid file."
+
+    try:
+        # Load audio
+        waveform, sample_rate = torchaudio.load(audio)
+
+        # Ensure correct sample rate (16kHz expected)
+        if sample_rate != 16000:
+            waveform = torchaudio.transforms.Resample(orig_freq=sample_rate, new_freq=16000)(waveform)
+
+        # Transcribe
+        transcription = asr_model.transcribe_batch(waveform)
+        return transcription[0]
+
+    except Exception as e:
+        return f"Error processing audio: {str(e)}"
 
-# Interface Gradio
+# Create Gradio Interface
 iface = gr.Interface(
     fn=transcribe,
-    inputs = gr.Audio(type="filepath"),
+    inputs=gr.Audio(type="filepath"),
     outputs="text",
     title="Reconnaissance Vocale Darija",
     description="Parlez en Darija et obtenez la transcription."
 )
 
-iface.launch()
+# Launch the app
+if __name__ == "__main__":
+    iface.launch()