Update app.py

app.py

@@ -1,19 +1,14 @@
-import gradio as gr
-from transformers import pipeline
+from speechbrain.pretrained import EncoderASR
+import soundfile as sf
 
-image_classifier = pipeline(task="image-classification", model="models/aioxlabs/dvoice-darija")
+# Load the pretrained ASR model
+asr_model = EncoderASR.from_hparams(source="aioxlabs/dvoice-darija", savedir="pretrained_models/asr-wav2vec2-dvoice-dar")
 
-def predict(input_img):
-    predictions = image_classifier(input_img)
-    return input_img, {p["label"]: p["score"] for p in predictions}
+# Load the audio file
+audio_input, _ = sf.read("kanbghik.mp3")
 
-gr_interface = gr.Interface(
-    predict,
-    inputs=gr.inputs.Image(label="Select hot dog candidate", source=['upload', 'webcam'], type="pil"),
-    outputs=[gr.outputs.Image(label="Processed Image"), gr.outputs.Label(label="Result", num_top_classes=2)],
-    title="Hot Dog? Or Not?",
-)
+# Transcribe the audio
+transcription = asr_model.transcribe_file("kanbghik.mp3")
 
-if __name__ == "__main__":
-    gr_interface.launch()
+print("Transcription:", transcription)