offline experience fixes (#2711)

Author: eaidova

notebooks/bark-text-to-audio/bark-text-to-audio.ipynb

@@ -142,7 +142,7 @@
    "source": [
     "text_use_small = True\n",
     "\n",
-    "text_encoder = load_model(model_type=\"text\", use_gpu=False, use_small=text_use_small, force_reload=False)\n",
+    "text_encoder = load_model(model_type=\"text\", use_gpu=False, use_small=text_use_small, force_reload=False, weights_only=False)\n",
     "\n",
     "text_encoder_model = text_encoder[\"model\"]\n",
     "tokenizer = text_encoder[\"tokenizer\"]"

notebooks/blip-visual-language-processing/blip-visual-language-processing.ipynb

@@ -1644,6 +1644,7 @@
     "\n",
     "comp_text_encoder = core.compile_model(TEXT_ENCODER_OV, device.value)\n",
     "comp_text_decoder_with_past = core.compile_model(TEXT_DECODER_OV, device.value)\n",
+    "comp_vision_model = core.compile_model(VISION_MODEL_OV, device.value)\n",
     "fp_text_decoder.forward = partial(text_decoder_forward, ov_text_decoder_with_past=comp_text_decoder_with_past)\n",
     "fp16_model = OVBlipModel(model.config, model.decoder_start_token_id, comp_vision_model, comp_text_encoder, fp_text_decoder)"
    ]

notebooks/depth-anything/depth-anything.ipynb

@@ -69,13 +69,7 @@
     "    r = requests.get(\n",
     "        url=\"https://raw.githubusercontent.com/openvinotoolkit/openvino_notebooks/latest/utils/cmd_helper.py\",\n",
     "    )\n",
-    "    open(\"cmd_helper.py\", \"w\").write(r.text)\n",
-    "\n",
-    "if not Path(\"notebook_utils.py\").exists():\n",
-    "    r = requests.get(\n",
-    "        url=\"https://raw.githubusercontent.com/openvinotoolkit/openvino_notebooks/latest/utils/notebook_utils.py\",\n",
-    "    )\n",
-    "    open(\"notebook_utils.py\", \"w\").write(r.text)"
+    "    open(\"cmd_helper.py\", \"w\").write(r.text)"
    ]
   },
   {
@@ -109,7 +103,13 @@
     "if platform.system() == \"Darwin\":\n",
     "    %pip install -q \"numpy<2.0.0\"\n",
     "if platform.python_version_tuple()[1] in [\"8\", \"9\"]:\n",
-    "    %pip install -q \"gradio-imageslider<=0.0.17\" \"typing-extensions>=4.9.0\""
+    "    %pip install -q \"gradio-imageslider<=0.0.17\" \"typing-extensions>=4.9.0\"\n",
+    "\n",
+    "if not Path(\"notebook_utils.py\").exists():\n",
+    "    r = requests.get(\n",
+    "        url=\"https://raw.githubusercontent.com/openvinotoolkit/openvino_notebooks/latest/utils/notebook_utils.py\",\n",
+    "    )\n",
+    "    open(\"notebook_utils.py\", \"w\").write(r.text)"
    ]
   },
   {

notebooks/instruct-pix2pix-image-editing/instruct-pix2pix-image-editing.ipynb

@@ -1080,12 +1080,13 @@
    "source": [
     "import io\n",
     "import requests\n",
+    "from diffusers.utils import load_image\n",
     "\n",
     "default_image_path = Path(\"default_image.png\")\n",
     "default_url = \"https://user-images.githubusercontent.com/29454499/223343459-4ac944f0-502e-4acf-9813-8e9f0abc8a16.jpg\"\n",
     "\n",
     "if not default_image_path.exists():\n",
-    "    img = PIL.Image.open(io.BytesIO(requests.get(default_url, stream=True).raw))\n",
+    "    img = load_image(default_url)\n",
     "    img.save(default_image_path)\n",
     "\n",
     "default_image = PIL.Image.open(default_image_path)\n",

notebooks/llm-agent-react/llm-agent-react-langchain.ipynb

@@ -486,6 +486,11 @@
     "import openvino.properties.hint as hints\n",
     "import openvino.properties.streams as streams\n",
     "\n",
+    "import torch\n",
+    "\n",
+    "if hasattr(torch, \"mps\") and torch.mps.is_available:\n",
+    "    torch.mps.is_available = lambda: False\n",
+    "\n",
     "\n",
     "class StopSequenceCriteria(StoppingCriteria):\n",
     "    \"\"\"\n",

notebooks/multimodal-rag/multimodal-rag-llamaindex.ipynb

@@ -605,6 +605,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "import torch\n",
+    "\n",
+    "if hasattr(torch, \"mps\") and torch.mps.is_available:\n",
+    "    torch.mps.is_available = lambda: False\n",
+    "\n",
     "from llama_index.core.indices import MultiModalVectorStoreIndex\n",
     "from llama_index.vector_stores.qdrant import QdrantVectorStore\n",
     "from llama_index.core import StorageContext, Settings\n",

notebooks/optical-character-recognition/optical-character-recognition.ipynb

@@ -94,7 +94,7 @@
     "    )\n",
     "\n",
     "    open(\"notebook_utils.py\", \"w\").write(r.text)\n",
-    "from notebook_utils import load_image, device_widget\n",
+    "from notebook_utils import download_file, device_widget\n",
     "\n",
     "# Read more about telemetry collection at https://github.com/openvinotoolkit/openvino_notebooks?tab=readme-ov-file#-telemetry\n",
     "from notebook_utils import collect_telemetry\n",
@@ -290,14 +290,14 @@
     }
    ],
    "source": [
-    "# The `image_file` variable can point to a URL or a local image.\n",
-    "image_url = \"https://storage.openvinotoolkit.org/repositories/openvino_notebooks/data/data/image/intel_rnb.jpg\"\n",
-    "\n",
     "image_path = Path(\"intel_rnb.jpg\")\n",
     "\n",
     "if not image_path.exists():\n",
-    "    image = load_image(image_url)\n",
-    "    cv2.imwrite(str(image_path), image)\n",
+    "    download_file(\n",
+    "        url=\"https://storage.openvinotoolkit.org/repositories/openvino_notebooks/data/data/image/intel_rnb.jpg\",\n",
+    "        filename=image_path.name,\n",
+    "        directory=image_path.parent,\n",
+    "    )\n",
     "else:\n",
     "    image = cv2.imread(str(image_path))\n",
     "\n",

notebooks/paddle-ocr-webcam/pre_post_processing.py

@@ -461,7 +461,7 @@ def draw_ocr_box_txt(image, boxes, txts, scores=None, drop_score=0.5, font_path=
                 try:
                     char_size = font.getbox(c)
                     y_idx = -1
-                except AttributeError:
+                except Exception:
                     char_size = font.getsize(c)
                     y_idx = 1
 

notebooks/softvc-voice-conversion/softvc-voice-conversion.ipynb

@@ -108,7 +108,7 @@
     "\n",
     "%pip install -q \"openvino>=2023.2.0\"\n",
     "clone_repo(\"https://github.com/svc-develop-team/so-vits-svc\", revision=\"4.1-Stable\", add_to_sys_path=False)\n",
-    "%pip install -q --extra-index-url https://download.pytorch.org/whl/cpu  tqdm librosa \"torch>=2.1.0\" \"torchaudio>=2.1.0\" faiss-cpu \"gradio>=4.19\" \"numpy>=1.23.5\" praat-parselmouth"
+    "%pip install -q --extra-index-url https://download.pytorch.org/whl/cpu  tqdm librosa \"torch>=2.1.0,<2.6.0\" \"torchaudio>=2.1.0,<2.6.0\" faiss-cpu \"gradio>=4.19\" \"numpy>=1.23.5\" praat-parselmouth"
    ]
   },
   {

notebooks/whisper-asr-genai/whisper-asr-genai.ipynb

@@ -243,6 +243,7 @@
    "source": [
     "from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq, pipeline\n",
     "from transformers.utils import logging\n",
+    "import torch\n",
     "\n",
     "processor = AutoProcessor.from_pretrained(model_id.value)\n",
     "\n",
@@ -253,7 +254,7 @@
     "    model=pt_model,\n",
     "    tokenizer=processor.tokenizer,\n",
     "    feature_extractor=processor.feature_extractor,\n",
-    "    device=\"cpu\",\n",
+    "    device=torch.device(\"cpu\"),\n",
     ")"
    ]
   },
@@ -1017,7 +1018,9 @@
     "      model=ov_model,\n",
     "      chunk_length_s=30,\n",
     "      tokenizer=ov_processor.tokenizer,\n",
-    "      feature_extractor=ov_processor.feature_extractor)\n",
+    "      feature_extractor=ov_processor.feature_extractor,\n",
+    "      device=torch.device(\"cpu\")\n",
+    "      )\n",
     "    try:\n",
     "        calibration_dataset = dataset = load_dataset(\"openslr/librispeech_asr\", \"clean\", split=\"validation\", streaming=True, trust_remote_code=True)\n",
     "        for sample in tqdm(islice(calibration_dataset, calibration_dataset_size), desc=\"Collecting calibration data\",\n",