add: model from training with hyper parameter epoch=120, batch=32 for SCB dataset and my own custom dataset

app.py

@@ -1,4 +1,5 @@
 import gradio as gr
+from PIL import Image
 import torch
 from ultralyticsplus import YOLO, render_result
 
@@ -11,23 +12,28 @@ def launch(
 ):
     try:
         model_path = "./models/student-behaviour-best.pt"
-        model = YOLO("yolov8n.pt")
+        model = YOLO(
+            "./student-behaviour-test-deploy/models/OWN-DATASET-640-e120-b32-best.pt"
+        )
+
+        # pil_image = Image.fromarray(image)
 
         results = model.predict(
             image, conf=conf_threshold, iou=iou_threshold, imgsz=image_size
         )
         box = results[0].boxes
-        print(box)
+        # print(box)
+
         render = render_result(model=model, image=image, result=results[0])
         return render
     except Exception as e:
-        print(e)
+        print("error", e)
         return "./download.jpeg"
 
 
 inputs = [
     gr.Image(type="filepath", label="Input Image"),
-    gr.Slider(minimum=320, maximum=1280, value=640, step=32, label="Image Size"),
+    gr.Slider(minimum=256, maximum=1280, value=640, step=32, label="Image Size"),
     gr.Slider(
         minimum=0.0, maximum=1.0, value=0.4, step=0.1, label="Confidence Threshold"
     ),

models/OWN-DATASET-640-e120-b32-best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b433715b811e36de8e8e83e89bc84e808a66b68055eb2e4925a9dd5c95f78da
+size 6260441

models/SCB-640-e120-b32-best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3297bff6efde17917d641eacf69137eee010ba34c17e837eff8721a3acc1ee0
+size 6260697

stream.py

@@ -0,0 +1,55 @@
+import gradio as gr
+from pydub import AudioSegment
+from time import sleep
+
+with gr.Blocks() as demo:
+    input_audio = gr.Audio(label="Input Audio", type="filepath", format="mp3")
+    with gr.Row():
+        with gr.Column():
+            stream_as_file_btn = gr.Button("Stream as File")
+            format = gr.Radio(["wav", "mp3"], value="wav", label="Format")
+            stream_as_file_output = gr.Audio(streaming=True)
+
+            def stream_file(audio_file, format):
+                audio = AudioSegment.from_file(audio_file)
+                i = 0
+                chunk_size = 1000
+                while chunk_size * i < len(audio):
+                    chunk = audio[chunk_size * i : chunk_size * (i + 1)]
+                    i += 1
+                    if chunk:
+                        file = f"/tmp/{i}.{format}"
+                        chunk.export(file, format=format)
+                        yield file
+                        sleep(0.5)
+
+            stream_as_file_btn.click(
+                stream_file, [input_audio, format], stream_as_file_output
+            )
+
+            gr.Examples(
+                [["audio/cantina.wav", "wav"], ["audio/cantina.wav", "mp3"]],
+                [input_audio, format],
+                fn=stream_file,
+                outputs=stream_as_file_output,
+            )
+
+        with gr.Column():
+            stream_as_bytes_btn = gr.Button("Stream as Bytes")
+            stream_as_bytes_output = gr.Audio(format="bytes", streaming=True)
+
+            def stream_bytes(audio_file):
+                chunk_size = 20_000
+                with open(audio_file, "rb") as f:
+                    while True:
+                        chunk = f.read(chunk_size)
+                        if chunk:
+                            yield chunk
+                            sleep(1)
+                        else:
+                            break
+
+            stream_as_bytes_btn.click(stream_bytes, input_audio, stream_as_bytes_output)
+
+if __name__ == "__main__":
+    demo.queue().launch()