Update app.py

app.py

@@ -1,12 +1,41 @@
 import gradio as gr
+from transformers import WhisperForConditionalGeneration
+from transformers import WhisperFeatureExtractor
+from transformers import WhisperTokenizer
+from transformers import pipeline
 
-def greet(name):
-    return "Hello " + name + "!"
+checkpoint = "tsobolev/whisper-small-ka"
 
-with gr.Blocks() as demo:
-    name = gr.Textbox(label="Name")
-    output = gr.Textbox(label="Output Box")
-    greet_btn = gr.Button("Greet")
-    greet_btn.click(fn=greet, inputs=name, outputs=output, api_name="greet")
+feature_extractor = WhisperFeatureExtractor.from_pretrained(checkpoint)
+tokenizer = WhisperTokenizer.from_pretrained(checkpoint, language="georgian", task="transcribe")
+model = WhisperForConditionalGeneration.from_pretrained(checkpoint)
+forced_decoder_ids = tokenizer.get_decoder_prompt_ids(language="georgian", task="transcribe")
+
+asr_pipe = pipeline(
+    "automatic-speech-recognition",
+    model=model,
+    feature_extractor=feature_extractor,
+    tokenizer=tokenizer,
+    chunk_length_s=30,
+    stride_length_s=(4, 2)
+)
+
+def transcribe_ge(speech):
+    text = asr_pipe(
+            '../input/sounds/geo.wav',
+            generate_kwargs={"forced_decoder_ids": forced_decoder_ids}
+    )["text"]
+    return text
+
+
+demo = gr.Blocks()
+
+with demo:
+    audio_file = gr.Audio(type="filepath")
+    text = gr.Textbox()
+
+    b1 = gr.Button("Recognize Georgian")
+
+    b1.click(transcribe_ge, inputs=audio_file, outputs=text)
 
 demo.launch()