Merge branch 'nm/update_outetts' of https://github.com/KodiaqQ/openvino_notebooks into nm/update_outetts

Author: nikita-malininn

.ci/ignore_treon_docker.txt

@@ -82,4 +82,5 @@ notebooks/llm-agent-react/llm-agent-react.ipynb
 notebooks/multilora-image-generation/multilora-image-generation.ipynb
 notebooks/llm-agent-react/llm-agent-react-langchain.ipynb
 notebooks/multimodal-rag/multimodal-rag-llamaindex.ipynb
-notebooks/llm-rag-langchain/llm-rag-langchain-genai.ipynb
+notebooks/llm-rag-langchain/llm-rag-langchain-genai.ipynb
+notebooks/ltx-video/ltx-video.ipynb

.ci/skipped_notebooks.yml

@@ -334,13 +334,6 @@
         - ubuntu-20.04
         - ubuntu-22.04
         - windows-2019
-- notebook: notebooks/openvoice/openvoice.ipynb
-  skips:
-    - os:
-        - macos-13
-        - ubuntu-20.04
-        - ubuntu-22.04
-        - windows-2019
 - notebook: notebooks/instant-id/instant-id.ipynb
   skips:
     - os:
@@ -569,4 +562,11 @@
 - notebook: notebooks/tensorflow-quantization-aware-training/tensorflow-quantization-aware-training.ipynb
   skips:
     - python:
-        - '3.12'
+        - '3.12'
+- notebook: notebooks/ltx-video/ltx-video.ipynb
+  skips:
+    - os:
+        - macos-13
+        - ubuntu-20.04
+        - ubuntu-22.04
+        - windows-2019

.ci/spellcheck/.pyspelling.wordlist.txt

@@ -183,6 +183,7 @@ DeciDiffusion's
 deduplicated
 DeepFloyd
 DeepLabV
+DeepSeek
 denoise
 denoised
 denoises
@@ -233,6 +234,7 @@ Downloader
 downloader
 downsample
 downsampled
+downscaling
 DPM
 DPO
 dpo
@@ -323,6 +325,7 @@ GPUs
 Gradio
 gradio
 grayscale
+grey
 GroundedSAM
 GroundingDINO
 gRPC
@@ -477,6 +480,7 @@ LoRAs
 lraspp
 LRASPP
 LTS
+LTX
 LSTM
 LSTMs
 Luo
@@ -664,6 +668,7 @@ parameterization
 parametrize
 Parler
 parsers
+patchifying
 perceptron
 Patil
 PEFT
@@ -832,6 +837,7 @@ Segmenter
 segmenter
 Segmind
 segmind
+selfattention
 serializable
 sft
 ShapeNet
@@ -861,6 +867,7 @@ sparsity
 Sparisty
 sparsified
 sparsify
+spatiotemporal
 spectrogram
 spectrograms
 SpeechBrain
@@ -978,6 +985,7 @@ uparrow
 upcast
 upcasts
 Upcroft
+updo
 upsample
 upsampled
 upsamples
@@ -988,6 +996,7 @@ upscales
 upscaling
 utils
 VAE
+VAE's
 Validator
 validator
 variational

notebooks/README.md

@@ -58,6 +58,7 @@
 - [Visual-language assistant with Llama-3.2-11B-Vision and OpenVINO](./mllama-3.2/mllama-3.2.ipynb)
 - [Visual-language assistant with MiniCPM-V2 and OpenVINO](./minicpm-v-multimodal-chatbot/minicpm-v-multimodal-chatbot.ipynb)
 - [Magika: AI powered fast and efficient file type identification using OpenVINO](./magika-content-type-recognition/magika-content-type-recognition.ipynb)
+- [LTX Video and OpenVINO™](./ltx-video/ltx-video.ipynb)
 - [Create a RAG system using OpenVINO and LlamaIndex](./llm-rag-llamaindex/llm-rag-llamaindex.ipynb)
 - [Create a RAG system using OpenVINO and LangChain](./llm-rag-langchain/llm-rag-langchain.ipynb)
 - [Create a RAG system using OpenVINO GenAI and LangChain](./llm-rag-langchain/llm-rag-langchain-genai.ipynb)
@@ -251,6 +252,7 @@
 - [Visual-language assistant with MiniCPM-V2 and OpenVINO](./minicpm-v-multimodal-chatbot/minicpm-v-multimodal-chatbot.ipynb)
 - [Industrial Meter Reader](./meter-reader/meter-reader.ipynb)
 - [Magika: AI powered fast and efficient file type identification using OpenVINO](./magika-content-type-recognition/magika-content-type-recognition.ipynb)
+- [LTX Video and OpenVINO™](./ltx-video/ltx-video.ipynb)
 - [Create a RAG system using OpenVINO and LlamaIndex](./llm-rag-llamaindex/llm-rag-llamaindex.ipynb)
 - [Create a RAG system using OpenVINO and LangChain](./llm-rag-langchain/llm-rag-langchain.ipynb)
 - [Create a RAG system using OpenVINO GenAI and LangChain](./llm-rag-langchain/llm-rag-langchain-genai.ipynb)

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

@@ -671,7 +671,6 @@
     "        semantic_history = None\n",
     "    encoded_text = np.ascontiguousarray(_tokenize(tokenizer, text)) + TEXT_ENCODING_OFFSET\n",
     "    if len(encoded_text) > 256:\n",
-    "        p = round((len(encoded_text) - 256) / len(encoded_text) * 100, 1)\n",
     "        encoded_text = encoded_text[:256]\n",
     "    encoded_text = np.pad(\n",
     "        encoded_text,\n",

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

@@ -1293,7 +1293,7 @@
    "source": [
     "%%skip not $to_quantize.value\n",
     "\n",
-    "if not TEXT_ENCODER_OV_INT8.exists()\n",
+    "if not TEXT_ENCODER_OV_INT8.exists():\n",
     "    text_encoder_dataset = nncf.Dataset(calibration_data, lambda x: x[\"text_encoder_inputs\"])\n",
     "    text_encoder_model = core.read_model(TEXT_ENCODER_OV)\n",
     "\n",

notebooks/clip-zero-shot-image-classification/clip-zero-shot-classification.ipynb

@@ -200,7 +200,7 @@
     "sample_path = Path(\"data/coco.jpg\")\n",
     "sample_path.parent.mkdir(parents=True, exist_ok=True)\n",
     "\n",
-    "if not sample_path.exists()\n",
+    "if not sample_path.exists():\n",
     "    r = requests.get(\"https://storage.openvinotoolkit.org/repositories/openvino_notebooks/data/data/image/coco.jpg\")\n",
     "\n",
     "    with sample_path.open(\"wb\") as f:\n",

notebooks/efficient-sam/gradio_helper.py

@@ -15,10 +15,11 @@ def get_examples():
     examples_dir = Path("examples")
     examples_dir.mkdir(exist_ok=True)
     for img_id, image_url in enumerate(example_images):
-        r = requests.get(image_url)
         img_path = examples_dir / f"example_{img_id}.jpg"
-        with img_path.open("wb") as f:
-            f.write(r.content)
+        if not img_path.exists():
+            r = requests.get(image_url)
+            with img_path.open("wb") as f:
+                f.write(r.content)
     return [[img] for img in examples_dir.glob("*.jpg")]
 
 

notebooks/fast-segment-anything/gradio_helper.py

@@ -2,14 +2,26 @@
 import gradio as gr
 from PIL import Image, ImageDraw
 import numpy as np
+from pathlib import Path
+import requests
 
 examples = [
     ["https://storage.openvinotoolkit.org/repositories/openvino_notebooks/data/data/image/coco_bike.jpg"],
     ["https://storage.openvinotoolkit.org/repositories/openvino_notebooks/data/data/image/empty_road_mapillary.jpg"],
     ["https://storage.openvinotoolkit.org/repositories/openvino_notebooks/data/data/image/wall.jpg"],
 ]
 
-last_image = examples[0][0]
+# last_image = examples[0][0]
+
+example_images = []
+for example_image_url in examples:
+    image_name = example_image_url[0].split("/")[-1]
+    if not Path(image_name).exists():
+        image = Image.open(requests.get(example_image_url[0], stream=True).raw)
+        image.save(image_name)
+    example_images.append([image_name])
+
+last_image = example_images[0][0]
 
 
 def select_point(img: Image.Image, point_type: str, evt: gr.SelectData) -> Image.Image:
@@ -70,7 +82,7 @@ def save_last_picked_image(img: Image.Image) -> None:
 def make_demo(fn: Callable, quantized: bool):
     with gr.Blocks(title="Fast SAM") as demo:
         with gr.Row(variant="panel"):
-            original_img = gr.Image(label="Input", value=examples[0][0], type="pil")
+            original_img = gr.Image(label="Input", type="pil")
             segmented_img = gr.Image(label="Segmentation Map", type="pil")
         with gr.Row():
             point_type = gr.Radio(
@@ -87,7 +99,7 @@ def make_demo(fn: Callable, quantized: bool):
             segment_button = gr.Button("Segment", variant="primary")
             clear_button = gr.Button("Clear points", variant="secondary")
         gr.Examples(
-            examples,
+            example_images,
             inputs=original_img,
             fn=save_last_picked_image,
             run_on_click=True,

notebooks/glm-edge-v/glm-edge-v.ipynb

@@ -64,31 +64,8 @@
    ],
    "source": [
     "%pip install -q \"torch>=2.1\" \"torchvision\" \"protobuf>=3.20\" \"gradio>=4.26\" \"Pillow\" \"accelerate\" \"tqdm\"  --extra-index-url https://download.pytorch.org/whl/cpu\n",
-    "%pip install -q \"openvino>=2024.5.0\" \"nncf>=2.14.0\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "bbe33d8a",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
-      "llama-index-embeddings-openvino 0.5.0 requires huggingface-hub<0.24.0,>=0.23.0, but you have huggingface-hub 0.26.3 which is incompatible.\n",
-      "mobileclip 0.1.0 requires timm>=0.9.5, but you have timm 0.4.12 which is incompatible.\n",
-      "mobileclip 0.1.0 requires torchvision==0.14.1, but you have torchvision 0.20.1+cpu which is incompatible.\n",
-      "optimum-intel 1.21.0.dev0+080180b requires transformers<4.47,>=4.36, but you have transformers 4.47.0.dev0 which is incompatible.\n",
-      "salesforce-lavis 1.0.2 requires transformers<4.27,>=4.25.0, but you have transformers 4.47.0.dev0 which is incompatible.\u001b[0m\u001b[31m\n",
-      "\u001b[0mNote: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
-   "source": [
-    "%pip install -q \"git+https://github.com/huggingface/transformers\""
+    "%pip install -q \"openvino>=2024.5.0\" \"nncf>=2.14.0\"\n",
+    "%pip install -q \"git+https://github.com/huggingface/transformers\"  --extra-index-url https://download.pytorch.org/whl/cpu"
    ]
   },
   {
@@ -105,7 +82,6 @@
     "    r = requests.get(url=\"https://raw.githubusercontent.com/openvinotoolkit/openvino_notebooks/latest/notebooks/glm-edge-v/glmv_helper.py\")\n",
     "    open(\"glmv_helper.py\", \"w\").write(r.text)\n",
     "\n",
-    "\n",
     "if not Path(\"gradio_helper.py\").exists():\n",
     "    r = requests.get(url=\"https://raw.githubusercontent.com/openvinotoolkit/openvino_notebooks/latest/notebooks/glm-edge-v/gradio_helper.py\")\n",
     "    open(\"gradio_helper.py\", \"w\").write(r.text)\n",
@@ -346,8 +322,14 @@
     "import requests\n",
     "from PIL import Image\n",
     "\n",
-    "url = \"https://github.com/openvinotoolkit/openvino_notebooks/assets/29454499/d5fbbd1a-d484-415c-88cb-9986625b7b11\"\n",
-    "image = Image.open(requests.get(url, stream=True).raw)\n",
+    "image_path = Path(\"cat.png\")\n",
+    "\n",
+    "if not image_path.exists():\n",
+    "    url = \"https://github.com/openvinotoolkit/openvino_notebooks/assets/29454499/d5fbbd1a-d484-415c-88cb-9986625b7b11\"\n",
+    "    image = Image.open(requests.get(url, stream=True).raw)\n",
+    "    image.save(image_path)\n",
+    "else:\n",
+    "    image = Image.open(image_path)\n",
     "\n",
     "query = \"Please describe this picture\"\n",
     "\n",