Add Gradio helpers - part 6 (#2325)

Ticket: CVS-147626

Notebooks:

1. magika-content-type-recognition/magika-content-type-recognition.ipynb
- minimal Gradio demo, helper not needed
2.
mms-massively-multilingual-speech/mms-massively-multilingual-speech.ipynb
3. mobilevlm-language-assistant/mobilevlm-language-assistant.ipynb -
minimal Gradio demo, helper not needed
4. music-generation/music-generation.ipynb - minimal Gradio demo, helper
not needed
5. named-entity-recognition/named-entity-recognition.ipynb - minimal
Gradio demo, helper not needed
6. nano-llava-multimodal-chatbot/nano-llava-multimodal-chatbot.ipynb
7. oneformer-segmentation/oneformer-segmentation.ipynb
8. openvoice/openvoice.ipynb
9. paint-by-example/paint-by-example.ipynb
10. parler-tts-text-to-speech/parler-tts-text-to-speech.ipynb

notebooks/magika-content-type-recognition/magika-content-type-recognition.ipynb

@@ -409,11 +409,11 @@
     "\n",
     "\n",
     "demo = gr.Interface(\n",
-    "    classify,\n",
-    "    [\n",
+    "    fn=classify,\n",
+    "    inputs=[\n",
     "        gr.File(label=\"Input file\", type=\"binary\"),\n",
     "    ],\n",
-    "    gr.Label(label=\"Result\"),\n",
+    "    outputs=gr.Label(label=\"Result\"),\n",
     "    examples=[[\"./README.md\"]],\n",
     "    allow_flagging=\"never\",\n",
     ")\n",
@@ -425,6 +425,17 @@
     "# demo.launch(server_name='your server name', server_port='server port in int')\n",
     "# Read more in the docs: https://gradio.app/docs/"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "914a8a84",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# please uncomment and run this cell for stopping gradio interface\n",
+    "# demo.close()"
+   ]
   }
  ],
  "metadata": {

notebooks/mms-massively-multilingual-speech/gradio_helper.py

@@ -0,0 +1,62 @@
+from typing import Callable
+import gradio as gr
+
+
+title = "MMS with Gradio"
+description = (
+    'Gradio Demo for MMS and OpenVINO™. Upload a source audio, then click the "Submit" button to detect a language ID and a transcription. '
+    "Make sure that the audio data is sampled to 16000 kHz. If this language has not been used before, it may take some time to prepare the ASR model."
+    "\n"
+    "> Note: In order to run quantized model to transcribe some language, first the quantized model for that specific language must be prepared."
+)
+
+
+def make_demo(fn: Callable, quantized: bool):
+    with gr.Blocks() as demo:
+        with gr.Row():
+            gr.Markdown(f"# {title}")
+        with gr.Row():
+            gr.Markdown(description)
+
+        with gr.Row():
+            with gr.Column():
+                audio = gr.Audio(label="Source Audio", type="filepath")
+                run_button = gr.Button(value="Run FP32")
+                # if quantized:
+                #     run_quantized_button = gr.Button(value="Run INT8")
+            with gr.Column():
+                detected_language = gr.Textbox(label="Detected language ID")
+                transcription = gr.Textbox(label="Transcription")
+                identification_time = gr.Textbox(label="Identification time")
+                transcription_time = gr.Textbox(label="Transcription time")
+        with gr.Row(visible=quantized):
+            with gr.Column():
+                run_quantized_button = gr.Button(value="Run INT8")
+            with gr.Column():
+                detected_language_quantized = gr.Textbox(label="Detected language ID (Quantized)")
+                transcription_quantized = gr.Textbox(label="Transcription (Quantized)")
+                identification_time_quantized = gr.Textbox(label="Identification time (Quantized)")
+                transcription_time_quantized = gr.Textbox(label="Transcription time (Quantized)")
+
+        run_button.click(
+            fn=fn,
+            inputs=[audio, gr.Number(0, visible=False)],
+            outputs=[
+                detected_language,
+                transcription,
+                identification_time,
+                transcription_time,
+            ],
+        )
+        if quantized:
+            run_quantized_button.click(
+                fn=fn,
+                inputs=[audio, gr.Number(1, visible=False)],
+                outputs=[
+                    detected_language_quantized,
+                    transcription_quantized,
+                    identification_time_quantized,
+                    transcription_time_quantized,
+                ],
+            )
+    return demo

notebooks/mms-massively-multilingual-speech/mms-massively-multilingual-speech.ipynb

@@ -1560,30 +1560,15 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "49f4b7871f18ab46",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2023-10-12T16:17:33.520443100Z",
-     "start_time": "2023-10-12T16:13:07.494290500Z"
-    },
-    "collapsed": false
-   },
+   "id": "26913187",
+   "metadata": {},
    "outputs": [],
    "source": [
     "import gradio as gr\n",
     "import librosa\n",
     "import time\n",
     "\n",
     "\n",
-    "title = \"MMS with Gradio\"\n",
-    "description = (\n",
-    "    'Gradio Demo for MMS and OpenVINO™. Upload a source audio, then click the \"Submit\" button to detect a language ID and a transcription. '\n",
-    "    \"Make sure that the audio data is sampled to 16000 kHz. If this language has not been used before, it may take some time to prepare the ASR model.\"\n",
-    "    \"\\n\"\n",
-    "    \"> Note: In order to run quantized model to transcribe some language, first the quantized model for that specific language must be prepared.\"\n",
-    ")\n",
-    "\n",
-    "\n",
     "current_state = {\n",
     "    \"fp32\": {\"model\": None, \"language\": None},\n",
     "    \"int8\": {\"model\": None, \"language\": None},\n",
@@ -1620,57 +1605,31 @@
     "        transcription,\n",
     "        identification_delta_time,\n",
     "        transcription_delta_time,\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "49f4b7871f18ab46",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-10-12T16:17:33.520443100Z",
+     "start_time": "2023-10-12T16:13:07.494290500Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "if not Path(\"gradio_helper.py\").exists():\n",
+    "    r = requests.get(\n",
+    "        url=\"https://raw.githubusercontent.com/openvinotoolkit/openvino_notebooks/latest/notebooks/mms-massively-multilingual-speech/gradio_helper.py\"\n",
     "    )\n",
+    "    open(\"gradio_helper.py\", \"w\").write(r.text)\n",
     "\n",
+    "from gradio_helper import make_demo\n",
     "\n",
-    "with gr.Blocks() as demo:\n",
-    "    with gr.Row():\n",
-    "        gr.Markdown(f\"# {title}\")\n",
-    "    with gr.Row():\n",
-    "        gr.Markdown(description)\n",
-    "\n",
-    "    run_button = {True: None, False: None}\n",
-    "    detected_language = {True: None, False: None}\n",
-    "    transcription = {True: None, False: None}\n",
-    "    identification_time = {True: None, False: None}\n",
-    "    transcription_time = {True: None, False: None}\n",
-    "    for quantized in [False, True]:\n",
-    "        if quantized and not to_quantize.value:\n",
-    "            break\n",
-    "        with gr.Row():\n",
-    "            with gr.Column():\n",
-    "                if not quantized:\n",
-    "                    audio = gr.Audio(label=\"Source Audio\", type=\"filepath\")\n",
-    "                run_button_name = \"Run INT8\" if quantized else \"Run FP32\" if to_quantize.value else \"Run\"\n",
-    "                run_button[quantized] = gr.Button(value=run_button_name)\n",
-    "            with gr.Column():\n",
-    "                detected_language[quantized] = gr.Textbox(label=f\"Detected language ID{' (Quantized)' if quantized else ''}\")\n",
-    "                transcription[quantized] = gr.Textbox(label=f\"Transcription{' (Quantized)' if quantized else ''}\")\n",
-    "                identification_time[quantized] = gr.Textbox(label=f\"Identification time{' (Quantized)' if quantized else ''}\")\n",
-    "                transcription_time[quantized] = gr.Textbox(label=f\"Transcription time{' (Quantized)' if quantized else ''}\")\n",
-    "\n",
-    "    run_button[False].click(\n",
-    "        infer,\n",
-    "        inputs=[audio, gr.Number(0, visible=False)],\n",
-    "        outputs=[\n",
-    "            detected_language[False],\n",
-    "            transcription[False],\n",
-    "            identification_time[False],\n",
-    "            transcription_time[False],\n",
-    "        ],\n",
-    "    )\n",
-    "    if to_quantize.value:\n",
-    "        run_button[True].click(\n",
-    "            infer,\n",
-    "            inputs=[audio, gr.Number(1, visible=False)],\n",
-    "            outputs=[\n",
-    "                detected_language[True],\n",
-    "                transcription[True],\n",
-    "                identification_time[True],\n",
-    "                transcription_time[True],\n",
-    "            ],\n",
-    "        )\n",
-    "\n",
+    "demo = make_demo(fn=infer, quantized=to_quantize.value)\n",
     "\n",
     "try:\n",
     "    demo.queue().launch(debug=True)\n",
@@ -1680,6 +1639,17 @@
     "# demo.launch(server_name='your server name', server_port='server port in int')\n",
     "# Read more in the docs: https://gradio.app/docs/"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "20105387",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# please uncomment and run this cell for stopping gradio interface\n",
+    "# demo.close()"
+   ]
   }
  ],
  "metadata": {

notebooks/mobilevlm-language-assistant/mobilevlm-language-assistant.ipynb

@@ -729,7 +729,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "9fe048d2-0bd4-4748-aaf5-af221e069333",
+   "id": "3517c889",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -761,13 +761,20 @@
     "    if outputs.endswith(stop_str):\n",
     "        outputs = outputs[: -len(stop_str)]\n",
     "\n",
-    "    return outputs.strip()\n",
-    "\n",
-    "\n",
+    "    return outputs.strip()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9fe048d2-0bd4-4748-aaf5-af221e069333",
+   "metadata": {},
+   "outputs": [],
+   "source": [
     "demo = gr.Interface(\n",
-    "    generate,\n",
-    "    [gr.Image(label=\"Image\", type=\"pil\"), gr.Textbox(label=\"Prompt\")],\n",
-    "    gr.Textbox(),\n",
+    "    fn=generate,\n",
+    "    inputs=[gr.Image(label=\"Image\", type=\"pil\"), gr.Textbox(label=\"Prompt\")],\n",
+    "    outputs=gr.Textbox(),\n",
     "    examples=[\n",
     "        [\n",
     "            str(IMAGE_PATH),\n",
@@ -785,6 +792,17 @@
     "# demo.launch(server_name='your server name', server_port='server port in int')\n",
     "# Read more in the docs: https://gradio.app/docs/"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "58eb46c9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# please uncomment and run this cell for stopping gradio interface\n",
+    "# demo.close()"
+   ]
   }
  ],
  "metadata": {

notebooks/music-generation/music-generation.ipynb

@@ -788,7 +788,7 @@
     "import gradio as gr\n",
     "\n",
     "demo = gr.Interface(\n",
-    "    _generate,\n",
+    "    fn=_generate,\n",
     "    inputs=[\n",
     "        gr.Textbox(label=\"Text Prompt\"),\n",
     "    ],\n",
@@ -810,6 +810,17 @@
     "# EXAMPLE: `demo.launch(server_name='your server name', server_port='server port in int')`\n",
     "# To learn more please refer to the Gradio docs: https://gradio.app/docs/"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cc027753",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# please uncomment and run this cell for stopping gradio interface\n",
+    "# demo.close()"
+   ]
   }
  ],
  "metadata": {

notebooks/named-entity-recognition/named-entity-recognition.ipynb

@@ -505,33 +505,40 @@
    "source": [
     "import gradio as gr\n",
     "\n",
-    "examples = [\n",
-    "    \"My name is Wolfgang and I live in Berlin.\",\n",
-    "]\n",
-    "\n",
     "\n",
     "def run_ner(text):\n",
     "    output = ner_pipeline_optimized(text)\n",
     "    return {\"text\": text, \"entities\": output}\n",
     "\n",
     "\n",
     "demo = gr.Interface(\n",
-    "    run_ner,\n",
-    "    gr.Textbox(placeholder=\"Enter sentence here...\", label=\"Input Text\"),\n",
-    "    gr.HighlightedText(label=\"Output Text\"),\n",
-    "    examples=examples,\n",
+    "    fn=run_ner,\n",
+    "    inputs=gr.Textbox(placeholder=\"Enter sentence here...\", label=\"Input Text\"),\n",
+    "    outputs=gr.HighlightedText(label=\"Output Text\"),\n",
+    "    examples=[\n",
+    "        \"My name is Wolfgang and I live in Berlin.\",\n",
+    "    ],\n",
     "    allow_flagging=\"never\",\n",
     ")\n",
     "\n",
-    "if __name__ == \"__main__\":\n",
-    "    try:\n",
-    "        demo.launch(debug=True)\n",
-    "    except Exception:\n",
-    "        demo.launch(share=True, debug=True)\n",
+    "try:\n",
+    "    demo.launch(debug=True)\n",
+    "except Exception:\n",
+    "    demo.launch(share=True, debug=True)\n",
     "# if you are launching remotely, specify server_name and server_port\n",
     "# demo.launch(server_name='your server name', server_port='server port in int')\n",
     "# Read more in the docs: https://gradio.app/docs/"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# please uncomment and run this cell for stopping gradio interface\n",
+    "# demo.close()"
+   ]
   }
  ],
  "metadata": {