Create app.py

app.py

@@ -0,0 +1,27 @@
+from transformers import pipeline
+import gradio as gr
+import librosa
+import numpy as np
+
+from transformers import WhisperProcessor, WhisperForConditionalGeneration, pipeline
+
+processor = WhisperProcessor.from_pretrained("https://huggingface.co/spaces/akadriu/shqip_whisper")
+model = WhisperForConditionalGeneration.from_pretrained("https://huggingface.co/spaces/akadriu/shqip_whisper")
+
+def transcribe(audio):
+    audio_input, _ = librosa.load(audio, sr=16000)
+    input_features = processor(audio_input, sampling_rate=16000, return_tensors="pt").input_features 
+    predicted_ids = model.generate(input_features)
+    transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
+    text = transcription
+    return text
+
+iface = gr.Interface(
+    fn=transcribe, 
+    inputs=gr.Audio(source="microphone", type="filepath"), 
+    outputs="text",
+    title="Whisper Medium Shqip",
+    description="Realtime demo for Sq speech recognition using a fine-tuned Whisper medium model.",
+)
+
+iface.launch()