diff --git "a/VitsModelSplit/PosteriorDecoderModel_notebook.ipynb" "b/VitsModelSplit/PosteriorDecoderModel_notebook.ipynb" new file mode 100644--- /dev/null +++ "b/VitsModelSplit/PosteriorDecoderModel_notebook.ipynb" @@ -0,0 +1,2724 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "language_info": { + "name": "python" + }, + "widgets": { + "application/vnd.jupyter.widget-state+json": { + "26eba4b916a14c09ba9349e5113991cf": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_1ba80f3aaff44ee1a65026a3bed54deb", + "IPY_MODEL_4ed0475a547c4584a1794a4a233d33a0", + "IPY_MODEL_c3356a69e8884755ab162cffc9537864" + ], + "layout": "IPY_MODEL_3f4d6f767c584b419e32259c2a3c7507" + } + }, + "1ba80f3aaff44ee1a65026a3bed54deb": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_eb66729fbb9c4e50893b61db2e850f5a", + "placeholder": "​", + "style": "IPY_MODEL_fcc817f28bf64c7ab45fc18c0f453169", + "value": "config.json: 100%" + } + }, + "4ed0475a547c4584a1794a4a233d33a0": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_083d10c2662645e789ca0c0b094bad4e", + "max": 1641, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_b0196e91e0b24273852fd20191ba2c0a", + "value": 1641 + } + }, + "c3356a69e8884755ab162cffc9537864": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_625cade43fff4db1893845bd22f19b48", + "placeholder": "​", + "style": "IPY_MODEL_bcb552d885374d778f7101dc1739a873", + "value": " 1.64k/1.64k [00:00<00:00, 41.3kB/s]" + } + }, + "3f4d6f767c584b419e32259c2a3c7507": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "eb66729fbb9c4e50893b61db2e850f5a": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "fcc817f28bf64c7ab45fc18c0f453169": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "083d10c2662645e789ca0c0b094bad4e": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "b0196e91e0b24273852fd20191ba2c0a": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "625cade43fff4db1893845bd22f19b48": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "bcb552d885374d778f7101dc1739a873": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "7e86843a0afe44a78210760a92411117": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_30c50b7d79eb45ebb5b82b0ec1209b60", + "IPY_MODEL_b9af9002372344fab8e91ee79ba90d81", + "IPY_MODEL_8ab1eb38be1b4ee29975de30a6323ab2" + ], + "layout": "IPY_MODEL_843bd27bdfc4439cb2e455f6f44eb8c1" + } + }, + "30c50b7d79eb45ebb5b82b0ec1209b60": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_404a3166f68e441ca60c057b75db0246", + "placeholder": "​", + "style": "IPY_MODEL_729309cfde0847849a4c83f2efb9789a", + "value": "model.safetensors: 100%" + } + }, + "b9af9002372344fab8e91ee79ba90d81": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_48409186bd234169a5fe43d207402b9a", + "max": 145228280, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_dd9e1951fc3742d19389dd59694fe2c6", + "value": 145228280 + } + }, + "8ab1eb38be1b4ee29975de30a6323ab2": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_84029ee47a594362bf0b2cdbc938e92d", + "placeholder": "​", + "style": "IPY_MODEL_234e7bbe055f4d208008bcf6af1bb948", + "value": " 145M/145M [00:03<00:00, 42.9MB/s]" + } + }, + "843bd27bdfc4439cb2e455f6f44eb8c1": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "404a3166f68e441ca60c057b75db0246": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "729309cfde0847849a4c83f2efb9789a": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "48409186bd234169a5fe43d207402b9a": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "dd9e1951fc3742d19389dd59694fe2c6": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "84029ee47a594362bf0b2cdbc938e92d": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "234e7bbe055f4d208008bcf6af1bb948": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "49f8d3d8cfe24b3a864cb57053db6788": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_724b19b41d414405a957674fe757bc73", + "IPY_MODEL_bba1f9ce5b3a4a94ad7a90954c6fcdb2", + "IPY_MODEL_b241ad516869421eb60047215535d3a6" + ], + "layout": "IPY_MODEL_5a07b1c4448e4bc39bfefa900287e5c4" + } + }, + "724b19b41d414405a957674fe757bc73": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_cf984c7ad36b47ca9758cd06c8f043f6", + "placeholder": "​", + "style": "IPY_MODEL_ba3ee841d8f641cb8bc891da306d1ca7", + "value": "tokenizer_config.json: 100%" + } + }, + "bba1f9ce5b3a4a94ad7a90954c6fcdb2": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_f24e65ce18f24159934d073d09a9414c", + "max": 288, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_f621895cecff4820a55445a0e9ccf0c7", + "value": 288 + } + }, + "b241ad516869421eb60047215535d3a6": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_4bc32474f2194649b21b5d5c9cb340c4", + "placeholder": "​", + "style": "IPY_MODEL_eaab7d543ed049f1b1efec7a4ef392ab", + "value": " 288/288 [00:00<00:00, 12.3kB/s]" + } + }, + "5a07b1c4448e4bc39bfefa900287e5c4": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "cf984c7ad36b47ca9758cd06c8f043f6": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "ba3ee841d8f641cb8bc891da306d1ca7": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "f24e65ce18f24159934d073d09a9414c": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "f621895cecff4820a55445a0e9ccf0c7": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "4bc32474f2194649b21b5d5c9cb340c4": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "eaab7d543ed049f1b1efec7a4ef392ab": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "86db1b1af2bc4643a505cad4d7135264": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_dd02bed5420f455a973f8367ff58cb33", + "IPY_MODEL_d51ed119dded4580af08c7d0ef325bb3", + "IPY_MODEL_7059bac41eff4acba94f86accd2e321b" + ], + "layout": "IPY_MODEL_6f80573093ce453f85117198766c0a38" + } + }, + "dd02bed5420f455a973f8367ff58cb33": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_5fba9b22d79e4d0ab2d7cebbe15ac706", + "placeholder": "​", + "style": "IPY_MODEL_4bf367cea86045b8bf23652308247077", + "value": "vocab.json: 100%" + } + }, + "d51ed119dded4580af08c7d0ef325bb3": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_f2c545f473bc4c33a54f94dd547ba998", + "max": 460, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_850f4bd076384ff995e7060f86bc5b77", + "value": 460 + } + }, + "7059bac41eff4acba94f86accd2e321b": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_848415b52eef472b91410eba506ab37b", + "placeholder": "​", + "style": "IPY_MODEL_1ef0e6f48df2488e96c5fca0a7be4286", + "value": " 460/460 [00:00<00:00, 17.0kB/s]" + } + }, + "6f80573093ce453f85117198766c0a38": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "5fba9b22d79e4d0ab2d7cebbe15ac706": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "4bf367cea86045b8bf23652308247077": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "f2c545f473bc4c33a54f94dd547ba998": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "850f4bd076384ff995e7060f86bc5b77": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "848415b52eef472b91410eba506ab37b": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "1ef0e6f48df2488e96c5fca0a7be4286": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "7b5037c1732441528d396fef9cced232": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_d7e73c62b5bc410aaacc037ba3fa435c", + "IPY_MODEL_4b737eee51a1497d977148d30dfe9bad", + "IPY_MODEL_8fa45d6a7cc14abb872ab180c5cb23f8" + ], + "layout": "IPY_MODEL_3ffee1d2c4a849a9b8df33039d86e945" + } + }, + "d7e73c62b5bc410aaacc037ba3fa435c": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_cf17edab22cc49efa594b41d41d1947f", + "placeholder": "​", + "style": "IPY_MODEL_169baa2ee62d4f9f96727fee72055d1d", + "value": "special_tokens_map.json: 100%" + } + }, + "4b737eee51a1497d977148d30dfe9bad": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_488409d44d024596adb7f6c8cc2261ab", + "max": 48, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_fa370520efe54f8cb5622817c4b59569", + "value": 48 + } + }, + "8fa45d6a7cc14abb872ab180c5cb23f8": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_9477a2ca9fe34b2495a9f4df9bfddcf9", + "placeholder": "​", + "style": "IPY_MODEL_46e0ed9fd82b45e2afdb8185655b8b8b", + "value": " 48.0/48.0 [00:00<00:00, 2.11kB/s]" + } + }, + "3ffee1d2c4a849a9b8df33039d86e945": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "cf17edab22cc49efa594b41d41d1947f": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "169baa2ee62d4f9f96727fee72055d1d": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "488409d44d024596adb7f6c8cc2261ab": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "fa370520efe54f8cb5622817c4b59569": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "9477a2ca9fe34b2495a9f4df9bfddcf9": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "46e0ed9fd82b45e2afdb8185655b8b8b": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + } + } + } + }, + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "jRiIYO86FZwj", + "outputId": "b1f47a80-f5c6-4520-d047-c4f9206e4e8b" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m510.5/510.5 kB\u001b[0m \u001b[31m5.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m116.3/116.3 kB\u001b[0m \u001b[31m8.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.1/194.1 kB\u001b[0m \u001b[31m5.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m9.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m297.4/297.4 kB\u001b[0m \u001b[31m3.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.2/2.2 MB\u001b[0m \u001b[31m10.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m207.3/207.3 kB\u001b[0m \u001b[31m14.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m267.1/267.1 kB\u001b[0m \u001b[31m12.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.7/62.7 kB\u001b[0m \u001b[31m6.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25h" + ] + } + ], + "source": [ + "!pip --q install datasets\n", + "!pip --q install accelerate\n", + "!pip --q install wandb" + ] + }, + { + "cell_type": "code", + "source": [ + "import warnings\n", + "warnings.filterwarnings(\"ignore\")\n", + "from IPython.display import Audio\n", + "import numpy as np\n", + "import torch\n", + "import pandas as pd\n", + "from datasets import DatasetDict,Dataset\n", + "import soundfile as sf\n", + "import os\n", + "import matplotlib.pyplot as plt\n", + "plt.style.use(\"seaborn-whitegrid\")\n" + ], + "metadata": { + "id": "L0mwyL-EFh2F" + }, + "execution_count": 2, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "from google.colab import drive\n", + "drive.mount('/content/drive')" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "W769XOa5Fhyl", + "outputId": "716d49d7-0f1a-47fb-e27f-68dbf1c41478" + }, + "execution_count": 3, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Mounted at /content/drive\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "!git clone https://github.com/Mahmood-Anaam/VitsModelSplit.git" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "5ZS8kVTJFhve", + "outputId": "9274f79e-a480-4d8e-a8fa-927947333f6f" + }, + "execution_count": 4, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Cloning into 'VitsModelSplit'...\n", + "remote: Enumerating objects: 181, done.\u001b[K\n", + "remote: Counting objects: 100% (181/181), done.\u001b[K\n", + "remote: Compressing objects: 100% (115/115), done.\u001b[K\n", + "remote: Total 181 (delta 109), reused 132 (delta 63), pack-reused 0\u001b[K\n", + "Receiving objects: 100% (181/181), 21.22 MiB | 40.46 MiB/s, done.\n", + "Resolving deltas: 100% (109/109), done.\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "\n", + "\n", + "---\n", + "\n" + ], + "metadata": { + "id": "Ed6KQi3bg4TS" + } + }, + { + "cell_type": "code", + "source": [ + "from VitsModelSplit.vits_model import VitsModel\n", + "from VitsModelSplit.PosteriorDecoderModel import PosteriorDecoderModel\n", + "from VitsModelSplit.feature_extraction import VitsFeatureExtractor\n", + "\n", + "from transformers import AutoTokenizer, HfArgumentParser, set_seed\n", + "from VitsModelSplit.Arguments import DataTrainingArguments, ModelArguments, VITSTrainingArguments\n" + ], + "metadata": { + "id": "-4aZETCsa3C4" + }, + "execution_count": 5, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "model = VitsModel.from_pretrained(\"facebook/mms-tts-ara\",cache_dir=\"./\")\n", + "tokenizer = AutoTokenizer.from_pretrained(\"facebook/mms-tts-ara\",cache_dir=\"./\")\n", + "feature_extractor = VitsFeatureExtractor()" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 284, + "referenced_widgets": [ + "26eba4b916a14c09ba9349e5113991cf", + "1ba80f3aaff44ee1a65026a3bed54deb", + "4ed0475a547c4584a1794a4a233d33a0", + "c3356a69e8884755ab162cffc9537864", + "3f4d6f767c584b419e32259c2a3c7507", + "eb66729fbb9c4e50893b61db2e850f5a", + "fcc817f28bf64c7ab45fc18c0f453169", + "083d10c2662645e789ca0c0b094bad4e", + "b0196e91e0b24273852fd20191ba2c0a", + "625cade43fff4db1893845bd22f19b48", + "bcb552d885374d778f7101dc1739a873", + "7e86843a0afe44a78210760a92411117", + "30c50b7d79eb45ebb5b82b0ec1209b60", + "b9af9002372344fab8e91ee79ba90d81", + "8ab1eb38be1b4ee29975de30a6323ab2", + "843bd27bdfc4439cb2e455f6f44eb8c1", + "404a3166f68e441ca60c057b75db0246", + "729309cfde0847849a4c83f2efb9789a", + "48409186bd234169a5fe43d207402b9a", + "dd9e1951fc3742d19389dd59694fe2c6", + "84029ee47a594362bf0b2cdbc938e92d", + "234e7bbe055f4d208008bcf6af1bb948", + "49f8d3d8cfe24b3a864cb57053db6788", + "724b19b41d414405a957674fe757bc73", + "bba1f9ce5b3a4a94ad7a90954c6fcdb2", + "b241ad516869421eb60047215535d3a6", + "5a07b1c4448e4bc39bfefa900287e5c4", + "cf984c7ad36b47ca9758cd06c8f043f6", + "ba3ee841d8f641cb8bc891da306d1ca7", + "f24e65ce18f24159934d073d09a9414c", + "f621895cecff4820a55445a0e9ccf0c7", + "4bc32474f2194649b21b5d5c9cb340c4", + "eaab7d543ed049f1b1efec7a4ef392ab", + "86db1b1af2bc4643a505cad4d7135264", + "dd02bed5420f455a973f8367ff58cb33", + "d51ed119dded4580af08c7d0ef325bb3", + "7059bac41eff4acba94f86accd2e321b", + "6f80573093ce453f85117198766c0a38", + "5fba9b22d79e4d0ab2d7cebbe15ac706", + "4bf367cea86045b8bf23652308247077", + "f2c545f473bc4c33a54f94dd547ba998", + "850f4bd076384ff995e7060f86bc5b77", + "848415b52eef472b91410eba506ab37b", + "1ef0e6f48df2488e96c5fca0a7be4286", + "7b5037c1732441528d396fef9cced232", + "d7e73c62b5bc410aaacc037ba3fa435c", + "4b737eee51a1497d977148d30dfe9bad", + "8fa45d6a7cc14abb872ab180c5cb23f8", + "3ffee1d2c4a849a9b8df33039d86e945", + "cf17edab22cc49efa594b41d41d1947f", + "169baa2ee62d4f9f96727fee72055d1d", + "488409d44d024596adb7f6c8cc2261ab", + "fa370520efe54f8cb5622817c4b59569", + "9477a2ca9fe34b2495a9f4df9bfddcf9", + "46e0ed9fd82b45e2afdb8185655b8b8b" + ] + }, + "id": "W5cH1Yvyb6It", + "outputId": "82837eb5-2753-4c8c-954d-96fb26e6abb3" + }, + "execution_count": 6, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "config.json: 0%| | 0.00/1.64k [00:00" + ], + "text/html": [ + "\n", + " \n", + " " + ] + }, + "metadata": {}, + "execution_count": 9 + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "\n", + "\n", + "---\n", + "\n" + ], + "metadata": { + "id": "Fx1HrDAdtOfX" + } + }, + { + "cell_type": "code", + "source": [ + "dataset_dir = '/content/drive/MyDrive/FeaturesCollectionDataset'\n", + "\n", + "posterior_decoder_model.train(True)\n", + "\n", + "posterior_decoder_model.trainer(\n", + " train_dataset_dir = os.path.join(dataset_dir,'train'),\n", + " eval_dataset_dir = os.path.join(dataset_dir,'eval'),\n", + " full_generation_dir = os.path.join(dataset_dir,'full_generation'),\n", + " feature_extractor = VitsFeatureExtractor(),\n", + " training_args = training_args,\n", + " full_generation_sample_index= 0,\n", + " project_name = \"Posterior_Decoder_Finetuning\",\n", + " wandbKey = \"782b6a6e82bbb5a5348de0d3c7d40d1e76351e79\",\n", + " )\n", + "\n", + "posterior_decoder_model.train(False)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1000 + }, + "id": "GmD2CSxbb5_G", + "outputId": "aecc974a-5c93-4e16-da21-af4452d1f2e4" + }, + "execution_count": 10, + "outputs": [ + { + "output_type": "stream", + "name": "stderr", + "text": [ + "\u001b[34m\u001b[1mwandb\u001b[0m: W&B API key is configured. Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m If you're specifying your api key in code, ensure this code is not shared publicly.\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Consider setting the WANDB_API_KEY environment variable, or running `wandb login` from the command line.\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: Appending key for api.wandb.ai to your netrc file: /root/.netrc\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33mmodelasg\u001b[0m. Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "Tracking run with wandb version 0.16.6" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "Run data is saved locally in /content/wandb/run-20240412_020441-twr08lud" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "Syncing run dainty-brook-37 to Weights & Biases (docs)
" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + " View project at https://wandb.ai/modelasg/Posterior_Decoder_Finetuning" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + " View run at https://wandb.ai/modelasg/Posterior_Decoder_Finetuning/runs/twr08lud" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "TRAINIG - batch 0, waveform torch.Size([10, 83040, 1]), step_loss_mel 0.6283440589904785, lr 1.99975e-05... \n", + "TRAINIG - batch 1, waveform torch.Size([10, 135680, 1]), step_loss_mel 0.6494752764701843, lr 1.99975e-05... \n", + "TRAINIG - batch 2, waveform torch.Size([10, 52036, 1]), step_loss_mel 0.6461055874824524, lr 1.99975e-05... \n", + "TRAINIG - batch 3, waveform torch.Size([10, 62720, 1]), step_loss_mel 0.5772804021835327, lr 1.99975e-05... \n", + "TRAINIG - batch 4, waveform torch.Size([6, 46560, 1]), step_loss_mel 0.6477117538452148, lr 1.99975e-05... \n", + "VALIDATION - batch 0, waveform torch.Size([10, 67200, 1]), step_loss_mel 0.6477117538452148 ... \n", + "VALIDATION - batch 1, waveform torch.Size([4, 67520, 1]), step_loss_mel 0.5747188329696655 ... \n", + "TRAINIG - batch 5, waveform torch.Size([10, 138560, 1]), step_loss_mel 0.5918751358985901, lr 1.99975e-05... \n", + "TRAINIG - batch 0, waveform torch.Size([10, 83040, 1]), step_loss_mel 0.5546226501464844, lr 1.99950003125e-05... \n", + "TRAINIG - batch 1, waveform torch.Size([10, 135680, 1]), step_loss_mel 0.5856809020042419, lr 1.99950003125e-05... \n", + "TRAINIG - batch 2, waveform torch.Size([10, 52036, 1]), step_loss_mel 0.5916953086853027, lr 1.99950003125e-05... \n", + "TRAINIG - batch 3, waveform torch.Size([10, 62720, 1]), step_loss_mel 0.5707828998565674, lr 1.99950003125e-05... \n", + "VALIDATION - batch 0, waveform torch.Size([10, 67200, 1]), step_loss_mel 0.5707828998565674 ... \n", + "VALIDATION - batch 1, waveform torch.Size([4, 67520, 1]), step_loss_mel 0.5912371277809143 ... \n", + "TRAINIG - batch 4, waveform torch.Size([6, 46560, 1]), step_loss_mel 0.5765572786331177, lr 1.99950003125e-05... \n", + "TRAINIG - batch 5, waveform torch.Size([10, 138560, 1]), step_loss_mel 0.5534473061561584, lr 1.99950003125e-05... \n", + "TRAINIG - batch 0, waveform torch.Size([10, 83040, 1]), step_loss_mel 0.5429945588111877, lr 1.9992500937460937e-05... \n", + "TRAINIG - batch 1, waveform torch.Size([10, 135680, 1]), step_loss_mel 0.5512351989746094, lr 1.9992500937460937e-05... \n", + "TRAINIG - batch 2, waveform torch.Size([10, 52036, 1]), step_loss_mel 0.5699723958969116, lr 1.9992500937460937e-05... \n", + "VALIDATION - batch 0, waveform torch.Size([10, 67200, 1]), step_loss_mel 0.5699723958969116 ... \n", + "VALIDATION - batch 1, waveform torch.Size([4, 67520, 1]), step_loss_mel 0.5864882469177246 ... \n", + "TRAINIG - batch 3, waveform torch.Size([10, 62720, 1]), step_loss_mel 0.5551315546035767, lr 1.9992500937460937e-05... \n", + "TRAINIG - batch 4, waveform torch.Size([6, 46560, 1]), step_loss_mel 0.5773655772209167, lr 1.9992500937460937e-05... \n", + "TRAINIG - batch 5, waveform torch.Size([10, 138560, 1]), step_loss_mel 0.5770468711853027, lr 1.9992500937460937e-05... \n" + ] + }, + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "PosteriorDecoderModel(\n", + " (posterior_encoder): VitsPosteriorEncoder(\n", + " (conv_pre): Conv1d(513, 192, kernel_size=(1,), stride=(1,))\n", + " (wavenet): VitsWaveNet(\n", + " (in_layers): ModuleList(\n", + " (0-15): 16 x ParametrizedConv1d(\n", + " 192, 384, kernel_size=(5,), stride=(1,), padding=(2,)\n", + " (parametrizations): ModuleDict(\n", + " (weight): ParametrizationList(\n", + " (0): _WeightNorm()\n", + " )\n", + " )\n", + " )\n", + " )\n", + " (res_skip_layers): ModuleList(\n", + " (0-14): 15 x ParametrizedConv1d(\n", + " 192, 384, kernel_size=(1,), stride=(1,)\n", + " (parametrizations): ModuleDict(\n", + " (weight): ParametrizationList(\n", + " (0): _WeightNorm()\n", + " )\n", + " )\n", + " )\n", + " (15): ParametrizedConv1d(\n", + " 192, 192, kernel_size=(1,), stride=(1,)\n", + " (parametrizations): ModuleDict(\n", + " (weight): ParametrizationList(\n", + " (0): _WeightNorm()\n", + " )\n", + " )\n", + " )\n", + " )\n", + " (dropout): Dropout(p=0.0, inplace=False)\n", + " )\n", + " (conv_proj): Conv1d(192, 384, kernel_size=(1,), stride=(1,))\n", + " )\n", + " (decoder): VitsHifiGan(\n", + " (conv_pre): Conv1d(192, 512, kernel_size=(7,), stride=(1,), padding=(3,))\n", + " (upsampler): ModuleList(\n", + " (0): ConvTranspose1d(512, 256, kernel_size=(16,), stride=(8,), padding=(4,))\n", + " (1): ConvTranspose1d(256, 128, kernel_size=(16,), stride=(8,), padding=(4,))\n", + " (2): ConvTranspose1d(128, 64, kernel_size=(4,), stride=(2,), padding=(1,))\n", + " (3): ConvTranspose1d(64, 32, kernel_size=(4,), stride=(2,), padding=(1,))\n", + " )\n", + " (resblocks): ModuleList(\n", + " (0): HifiGanResidualBlock(\n", + " (convs1): ModuleList(\n", + " (0): Conv1d(256, 256, kernel_size=(3,), stride=(1,), padding=(1,))\n", + " (1): Conv1d(256, 256, kernel_size=(3,), stride=(1,), padding=(3,), dilation=(3,))\n", + " (2): Conv1d(256, 256, kernel_size=(3,), stride=(1,), padding=(5,), dilation=(5,))\n", + " )\n", + " (convs2): ModuleList(\n", + " (0-2): 3 x Conv1d(256, 256, kernel_size=(3,), stride=(1,), padding=(1,))\n", + " )\n", + " )\n", + " (1): HifiGanResidualBlock(\n", + " (convs1): ModuleList(\n", + " (0): Conv1d(256, 256, kernel_size=(7,), stride=(1,), padding=(3,))\n", + " (1): Conv1d(256, 256, kernel_size=(7,), stride=(1,), padding=(9,), dilation=(3,))\n", + " (2): Conv1d(256, 256, kernel_size=(7,), stride=(1,), padding=(15,), dilation=(5,))\n", + " )\n", + " (convs2): ModuleList(\n", + " (0-2): 3 x Conv1d(256, 256, kernel_size=(7,), stride=(1,), padding=(3,))\n", + " )\n", + " )\n", + " (2): HifiGanResidualBlock(\n", + " (convs1): ModuleList(\n", + " (0): Conv1d(256, 256, kernel_size=(11,), stride=(1,), padding=(5,))\n", + " (1): Conv1d(256, 256, kernel_size=(11,), stride=(1,), padding=(15,), dilation=(3,))\n", + " (2): Conv1d(256, 256, kernel_size=(11,), stride=(1,), padding=(25,), dilation=(5,))\n", + " )\n", + " (convs2): ModuleList(\n", + " (0-2): 3 x Conv1d(256, 256, kernel_size=(11,), stride=(1,), padding=(5,))\n", + " )\n", + " )\n", + " (3): HifiGanResidualBlock(\n", + " (convs1): ModuleList(\n", + " (0): Conv1d(128, 128, kernel_size=(3,), stride=(1,), padding=(1,))\n", + " (1): Conv1d(128, 128, kernel_size=(3,), stride=(1,), padding=(3,), dilation=(3,))\n", + " (2): Conv1d(128, 128, kernel_size=(3,), stride=(1,), padding=(5,), dilation=(5,))\n", + " )\n", + " (convs2): ModuleList(\n", + " (0-2): 3 x Conv1d(128, 128, kernel_size=(3,), stride=(1,), padding=(1,))\n", + " )\n", + " )\n", + " (4): HifiGanResidualBlock(\n", + " (convs1): ModuleList(\n", + " (0): Conv1d(128, 128, kernel_size=(7,), stride=(1,), padding=(3,))\n", + " (1): Conv1d(128, 128, kernel_size=(7,), stride=(1,), padding=(9,), dilation=(3,))\n", + " (2): Conv1d(128, 128, kernel_size=(7,), stride=(1,), padding=(15,), dilation=(5,))\n", + " )\n", + " (convs2): ModuleList(\n", + " (0-2): 3 x Conv1d(128, 128, kernel_size=(7,), stride=(1,), padding=(3,))\n", + " )\n", + " )\n", + " (5): HifiGanResidualBlock(\n", + " (convs1): ModuleList(\n", + " (0): Conv1d(128, 128, kernel_size=(11,), stride=(1,), padding=(5,))\n", + " (1): Conv1d(128, 128, kernel_size=(11,), stride=(1,), padding=(15,), dilation=(3,))\n", + " (2): Conv1d(128, 128, kernel_size=(11,), stride=(1,), padding=(25,), dilation=(5,))\n", + " )\n", + " (convs2): ModuleList(\n", + " (0-2): 3 x Conv1d(128, 128, kernel_size=(11,), stride=(1,), padding=(5,))\n", + " )\n", + " )\n", + " (6): HifiGanResidualBlock(\n", + " (convs1): ModuleList(\n", + " (0): Conv1d(64, 64, kernel_size=(3,), stride=(1,), padding=(1,))\n", + " (1): Conv1d(64, 64, kernel_size=(3,), stride=(1,), padding=(3,), dilation=(3,))\n", + " (2): Conv1d(64, 64, kernel_size=(3,), stride=(1,), padding=(5,), dilation=(5,))\n", + " )\n", + " (convs2): ModuleList(\n", + " (0-2): 3 x Conv1d(64, 64, kernel_size=(3,), stride=(1,), padding=(1,))\n", + " )\n", + " )\n", + " (7): HifiGanResidualBlock(\n", + " (convs1): ModuleList(\n", + " (0): Conv1d(64, 64, kernel_size=(7,), stride=(1,), padding=(3,))\n", + " (1): Conv1d(64, 64, kernel_size=(7,), stride=(1,), padding=(9,), dilation=(3,))\n", + " (2): Conv1d(64, 64, kernel_size=(7,), stride=(1,), padding=(15,), dilation=(5,))\n", + " )\n", + " (convs2): ModuleList(\n", + " (0-2): 3 x Conv1d(64, 64, kernel_size=(7,), stride=(1,), padding=(3,))\n", + " )\n", + " )\n", + " (8): HifiGanResidualBlock(\n", + " (convs1): ModuleList(\n", + " (0): Conv1d(64, 64, kernel_size=(11,), stride=(1,), padding=(5,))\n", + " (1): Conv1d(64, 64, kernel_size=(11,), stride=(1,), padding=(15,), dilation=(3,))\n", + " (2): Conv1d(64, 64, kernel_size=(11,), stride=(1,), padding=(25,), dilation=(5,))\n", + " )\n", + " (convs2): ModuleList(\n", + " (0-2): 3 x Conv1d(64, 64, kernel_size=(11,), stride=(1,), padding=(5,))\n", + " )\n", + " )\n", + " (9): HifiGanResidualBlock(\n", + " (convs1): ModuleList(\n", + " (0): Conv1d(32, 32, kernel_size=(3,), stride=(1,), padding=(1,))\n", + " (1): Conv1d(32, 32, kernel_size=(3,), stride=(1,), padding=(3,), dilation=(3,))\n", + " (2): Conv1d(32, 32, kernel_size=(3,), stride=(1,), padding=(5,), dilation=(5,))\n", + " )\n", + " (convs2): ModuleList(\n", + " (0-2): 3 x Conv1d(32, 32, kernel_size=(3,), stride=(1,), padding=(1,))\n", + " )\n", + " )\n", + " (10): HifiGanResidualBlock(\n", + " (convs1): ModuleList(\n", + " (0): Conv1d(32, 32, kernel_size=(7,), stride=(1,), padding=(3,))\n", + " (1): Conv1d(32, 32, kernel_size=(7,), stride=(1,), padding=(9,), dilation=(3,))\n", + " (2): Conv1d(32, 32, kernel_size=(7,), stride=(1,), padding=(15,), dilation=(5,))\n", + " )\n", + " (convs2): ModuleList(\n", + " (0-2): 3 x Conv1d(32, 32, kernel_size=(7,), stride=(1,), padding=(3,))\n", + " )\n", + " )\n", + " (11): HifiGanResidualBlock(\n", + " (convs1): ModuleList(\n", + " (0): Conv1d(32, 32, kernel_size=(11,), stride=(1,), padding=(5,))\n", + " (1): Conv1d(32, 32, kernel_size=(11,), stride=(1,), padding=(15,), dilation=(3,))\n", + " (2): Conv1d(32, 32, kernel_size=(11,), stride=(1,), padding=(25,), dilation=(5,))\n", + " )\n", + " (convs2): ModuleList(\n", + " (0-2): 3 x Conv1d(32, 32, kernel_size=(11,), stride=(1,), padding=(5,))\n", + " )\n", + " )\n", + " )\n", + " (conv_post): Conv1d(32, 1, kernel_size=(7,), stride=(1,), padding=(3,), bias=False)\n", + " )\n", + ")" + ] + }, + "metadata": {}, + "execution_count": 10 + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "\n", + "\n", + "---\n", + "\n" + ], + "metadata": { + "id": "Ei01IXslBLEQ" + } + }, + { + "cell_type": "code", + "source": [ + "model_new = VitsModel.from_pretrained(\"facebook/mms-tts-ara\",cache_dir=\"./\")\n", + "model_new.posterior_encoder = posterior_decoder_model.posterior_encoder.to(model_new.device)\n", + "model_new.decoder = posterior_decoder_model.decoder.to(model_new.device)" + ], + "metadata": { + "id": "XfKRl6eLBKCU", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "814f01e1-06aa-411b-9d1d-1814cd7e5ef4" + }, + "execution_count": 11, + "outputs": [ + { + "output_type": "stream", + "name": "stderr", + "text": [ + "Some weights of the model checkpoint at facebook/mms-tts-ara were not used when initializing VitsModel: ['flow.flows.0.wavenet.in_layers.0.weight_g', 'flow.flows.0.wavenet.in_layers.0.weight_v', 'flow.flows.0.wavenet.in_layers.1.weight_g', 'flow.flows.0.wavenet.in_layers.1.weight_v', 'flow.flows.0.wavenet.in_layers.2.weight_g', 'flow.flows.0.wavenet.in_layers.2.weight_v', 'flow.flows.0.wavenet.in_layers.3.weight_g', 'flow.flows.0.wavenet.in_layers.3.weight_v', 'flow.flows.0.wavenet.res_skip_layers.0.weight_g', 'flow.flows.0.wavenet.res_skip_layers.0.weight_v', 'flow.flows.0.wavenet.res_skip_layers.1.weight_g', 'flow.flows.0.wavenet.res_skip_layers.1.weight_v', 'flow.flows.0.wavenet.res_skip_layers.2.weight_g', 'flow.flows.0.wavenet.res_skip_layers.2.weight_v', 'flow.flows.0.wavenet.res_skip_layers.3.weight_g', 'flow.flows.0.wavenet.res_skip_layers.3.weight_v', 'flow.flows.1.wavenet.in_layers.0.weight_g', 'flow.flows.1.wavenet.in_layers.0.weight_v', 'flow.flows.1.wavenet.in_layers.1.weight_g', 'flow.flows.1.wavenet.in_layers.1.weight_v', 'flow.flows.1.wavenet.in_layers.2.weight_g', 'flow.flows.1.wavenet.in_layers.2.weight_v', 'flow.flows.1.wavenet.in_layers.3.weight_g', 'flow.flows.1.wavenet.in_layers.3.weight_v', 'flow.flows.1.wavenet.res_skip_layers.0.weight_g', 'flow.flows.1.wavenet.res_skip_layers.0.weight_v', 'flow.flows.1.wavenet.res_skip_layers.1.weight_g', 'flow.flows.1.wavenet.res_skip_layers.1.weight_v', 'flow.flows.1.wavenet.res_skip_layers.2.weight_g', 'flow.flows.1.wavenet.res_skip_layers.2.weight_v', 'flow.flows.1.wavenet.res_skip_layers.3.weight_g', 'flow.flows.1.wavenet.res_skip_layers.3.weight_v', 'flow.flows.2.wavenet.in_layers.0.weight_g', 'flow.flows.2.wavenet.in_layers.0.weight_v', 'flow.flows.2.wavenet.in_layers.1.weight_g', 'flow.flows.2.wavenet.in_layers.1.weight_v', 'flow.flows.2.wavenet.in_layers.2.weight_g', 'flow.flows.2.wavenet.in_layers.2.weight_v', 'flow.flows.2.wavenet.in_layers.3.weight_g', 'flow.flows.2.wavenet.in_layers.3.weight_v', 'flow.flows.2.wavenet.res_skip_layers.0.weight_g', 'flow.flows.2.wavenet.res_skip_layers.0.weight_v', 'flow.flows.2.wavenet.res_skip_layers.1.weight_g', 'flow.flows.2.wavenet.res_skip_layers.1.weight_v', 'flow.flows.2.wavenet.res_skip_layers.2.weight_g', 'flow.flows.2.wavenet.res_skip_layers.2.weight_v', 'flow.flows.2.wavenet.res_skip_layers.3.weight_g', 'flow.flows.2.wavenet.res_skip_layers.3.weight_v', 'flow.flows.3.wavenet.in_layers.0.weight_g', 'flow.flows.3.wavenet.in_layers.0.weight_v', 'flow.flows.3.wavenet.in_layers.1.weight_g', 'flow.flows.3.wavenet.in_layers.1.weight_v', 'flow.flows.3.wavenet.in_layers.2.weight_g', 'flow.flows.3.wavenet.in_layers.2.weight_v', 'flow.flows.3.wavenet.in_layers.3.weight_g', 'flow.flows.3.wavenet.in_layers.3.weight_v', 'flow.flows.3.wavenet.res_skip_layers.0.weight_g', 'flow.flows.3.wavenet.res_skip_layers.0.weight_v', 'flow.flows.3.wavenet.res_skip_layers.1.weight_g', 'flow.flows.3.wavenet.res_skip_layers.1.weight_v', 'flow.flows.3.wavenet.res_skip_layers.2.weight_g', 'flow.flows.3.wavenet.res_skip_layers.2.weight_v', 'flow.flows.3.wavenet.res_skip_layers.3.weight_g', 'flow.flows.3.wavenet.res_skip_layers.3.weight_v', 'posterior_encoder.wavenet.in_layers.0.weight_g', 'posterior_encoder.wavenet.in_layers.0.weight_v', 'posterior_encoder.wavenet.in_layers.1.weight_g', 'posterior_encoder.wavenet.in_layers.1.weight_v', 'posterior_encoder.wavenet.in_layers.10.weight_g', 'posterior_encoder.wavenet.in_layers.10.weight_v', 'posterior_encoder.wavenet.in_layers.11.weight_g', 'posterior_encoder.wavenet.in_layers.11.weight_v', 'posterior_encoder.wavenet.in_layers.12.weight_g', 'posterior_encoder.wavenet.in_layers.12.weight_v', 'posterior_encoder.wavenet.in_layers.13.weight_g', 'posterior_encoder.wavenet.in_layers.13.weight_v', 'posterior_encoder.wavenet.in_layers.14.weight_g', 'posterior_encoder.wavenet.in_layers.14.weight_v', 'posterior_encoder.wavenet.in_layers.15.weight_g', 'posterior_encoder.wavenet.in_layers.15.weight_v', 'posterior_encoder.wavenet.in_layers.2.weight_g', 'posterior_encoder.wavenet.in_layers.2.weight_v', 'posterior_encoder.wavenet.in_layers.3.weight_g', 'posterior_encoder.wavenet.in_layers.3.weight_v', 'posterior_encoder.wavenet.in_layers.4.weight_g', 'posterior_encoder.wavenet.in_layers.4.weight_v', 'posterior_encoder.wavenet.in_layers.5.weight_g', 'posterior_encoder.wavenet.in_layers.5.weight_v', 'posterior_encoder.wavenet.in_layers.6.weight_g', 'posterior_encoder.wavenet.in_layers.6.weight_v', 'posterior_encoder.wavenet.in_layers.7.weight_g', 'posterior_encoder.wavenet.in_layers.7.weight_v', 'posterior_encoder.wavenet.in_layers.8.weight_g', 'posterior_encoder.wavenet.in_layers.8.weight_v', 'posterior_encoder.wavenet.in_layers.9.weight_g', 'posterior_encoder.wavenet.in_layers.9.weight_v', 'posterior_encoder.wavenet.res_skip_layers.0.weight_g', 'posterior_encoder.wavenet.res_skip_layers.0.weight_v', 'posterior_encoder.wavenet.res_skip_layers.1.weight_g', 'posterior_encoder.wavenet.res_skip_layers.1.weight_v', 'posterior_encoder.wavenet.res_skip_layers.10.weight_g', 'posterior_encoder.wavenet.res_skip_layers.10.weight_v', 'posterior_encoder.wavenet.res_skip_layers.11.weight_g', 'posterior_encoder.wavenet.res_skip_layers.11.weight_v', 'posterior_encoder.wavenet.res_skip_layers.12.weight_g', 'posterior_encoder.wavenet.res_skip_layers.12.weight_v', 'posterior_encoder.wavenet.res_skip_layers.13.weight_g', 'posterior_encoder.wavenet.res_skip_layers.13.weight_v', 'posterior_encoder.wavenet.res_skip_layers.14.weight_g', 'posterior_encoder.wavenet.res_skip_layers.14.weight_v', 'posterior_encoder.wavenet.res_skip_layers.15.weight_g', 'posterior_encoder.wavenet.res_skip_layers.15.weight_v', 'posterior_encoder.wavenet.res_skip_layers.2.weight_g', 'posterior_encoder.wavenet.res_skip_layers.2.weight_v', 'posterior_encoder.wavenet.res_skip_layers.3.weight_g', 'posterior_encoder.wavenet.res_skip_layers.3.weight_v', 'posterior_encoder.wavenet.res_skip_layers.4.weight_g', 'posterior_encoder.wavenet.res_skip_layers.4.weight_v', 'posterior_encoder.wavenet.res_skip_layers.5.weight_g', 'posterior_encoder.wavenet.res_skip_layers.5.weight_v', 'posterior_encoder.wavenet.res_skip_layers.6.weight_g', 'posterior_encoder.wavenet.res_skip_layers.6.weight_v', 'posterior_encoder.wavenet.res_skip_layers.7.weight_g', 'posterior_encoder.wavenet.res_skip_layers.7.weight_v', 'posterior_encoder.wavenet.res_skip_layers.8.weight_g', 'posterior_encoder.wavenet.res_skip_layers.8.weight_v', 'posterior_encoder.wavenet.res_skip_layers.9.weight_g', 'posterior_encoder.wavenet.res_skip_layers.9.weight_v']\n", + "- This IS expected if you are initializing VitsModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n", + "- This IS NOT expected if you are initializing VitsModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n", + "Some weights of VitsModel were not initialized from the model checkpoint at facebook/mms-tts-ara and are newly initialized: ['discriminator.discriminators.0.convs.0.bias', 'discriminator.discriminators.0.convs.0.weight', 'discriminator.discriminators.0.convs.1.bias', 'discriminator.discriminators.0.convs.1.weight', 'discriminator.discriminators.0.convs.2.bias', 'discriminator.discriminators.0.convs.2.weight', 'discriminator.discriminators.0.convs.3.bias', 'discriminator.discriminators.0.convs.3.weight', 'discriminator.discriminators.0.convs.4.bias', 'discriminator.discriminators.0.convs.4.weight', 'discriminator.discriminators.0.convs.5.bias', 'discriminator.discriminators.0.convs.5.weight', 'discriminator.discriminators.0.final_conv.bias', 'discriminator.discriminators.0.final_conv.weight', 'discriminator.discriminators.1.convs.0.bias', 'discriminator.discriminators.1.convs.0.weight', 'discriminator.discriminators.1.convs.1.bias', 'discriminator.discriminators.1.convs.1.weight', 'discriminator.discriminators.1.convs.2.bias', 'discriminator.discriminators.1.convs.2.weight', 'discriminator.discriminators.1.convs.3.bias', 'discriminator.discriminators.1.convs.3.weight', 'discriminator.discriminators.1.convs.4.bias', 'discriminator.discriminators.1.convs.4.weight', 'discriminator.discriminators.1.final_conv.bias', 'discriminator.discriminators.1.final_conv.weight', 'discriminator.discriminators.2.convs.0.bias', 'discriminator.discriminators.2.convs.0.weight', 'discriminator.discriminators.2.convs.1.bias', 'discriminator.discriminators.2.convs.1.weight', 'discriminator.discriminators.2.convs.2.bias', 'discriminator.discriminators.2.convs.2.weight', 'discriminator.discriminators.2.convs.3.bias', 'discriminator.discriminators.2.convs.3.weight', 'discriminator.discriminators.2.convs.4.bias', 'discriminator.discriminators.2.convs.4.weight', 'discriminator.discriminators.2.final_conv.bias', 'discriminator.discriminators.2.final_conv.weight', 'discriminator.discriminators.3.convs.0.bias', 'discriminator.discriminators.3.convs.0.weight', 'discriminator.discriminators.3.convs.1.bias', 'discriminator.discriminators.3.convs.1.weight', 'discriminator.discriminators.3.convs.2.bias', 'discriminator.discriminators.3.convs.2.weight', 'discriminator.discriminators.3.convs.3.bias', 'discriminator.discriminators.3.convs.3.weight', 'discriminator.discriminators.3.convs.4.bias', 'discriminator.discriminators.3.convs.4.weight', 'discriminator.discriminators.3.final_conv.bias', 'discriminator.discriminators.3.final_conv.weight', 'discriminator.discriminators.4.convs.0.bias', 'discriminator.discriminators.4.convs.0.weight', 'discriminator.discriminators.4.convs.1.bias', 'discriminator.discriminators.4.convs.1.weight', 'discriminator.discriminators.4.convs.2.bias', 'discriminator.discriminators.4.convs.2.weight', 'discriminator.discriminators.4.convs.3.bias', 'discriminator.discriminators.4.convs.3.weight', 'discriminator.discriminators.4.convs.4.bias', 'discriminator.discriminators.4.convs.4.weight', 'discriminator.discriminators.4.final_conv.bias', 'discriminator.discriminators.4.final_conv.weight', 'discriminator.discriminators.5.convs.0.bias', 'discriminator.discriminators.5.convs.0.weight', 'discriminator.discriminators.5.convs.1.bias', 'discriminator.discriminators.5.convs.1.weight', 'discriminator.discriminators.5.convs.2.bias', 'discriminator.discriminators.5.convs.2.weight', 'discriminator.discriminators.5.convs.3.bias', 'discriminator.discriminators.5.convs.3.weight', 'discriminator.discriminators.5.convs.4.bias', 'discriminator.discriminators.5.convs.4.weight', 'discriminator.discriminators.5.final_conv.bias', 'discriminator.discriminators.5.final_conv.weight', 'flow.flows.0.wavenet.in_layers.0.parametrizations.weight.original0', 'flow.flows.0.wavenet.in_layers.0.parametrizations.weight.original1', 'flow.flows.0.wavenet.in_layers.1.parametrizations.weight.original0', 'flow.flows.0.wavenet.in_layers.1.parametrizations.weight.original1', 'flow.flows.0.wavenet.in_layers.2.parametrizations.weight.original0', 'flow.flows.0.wavenet.in_layers.2.parametrizations.weight.original1', 'flow.flows.0.wavenet.in_layers.3.parametrizations.weight.original0', 'flow.flows.0.wavenet.in_layers.3.parametrizations.weight.original1', 'flow.flows.0.wavenet.res_skip_layers.0.parametrizations.weight.original0', 'flow.flows.0.wavenet.res_skip_layers.0.parametrizations.weight.original1', 'flow.flows.0.wavenet.res_skip_layers.1.parametrizations.weight.original0', 'flow.flows.0.wavenet.res_skip_layers.1.parametrizations.weight.original1', 'flow.flows.0.wavenet.res_skip_layers.2.parametrizations.weight.original0', 'flow.flows.0.wavenet.res_skip_layers.2.parametrizations.weight.original1', 'flow.flows.0.wavenet.res_skip_layers.3.parametrizations.weight.original0', 'flow.flows.0.wavenet.res_skip_layers.3.parametrizations.weight.original1', 'flow.flows.1.wavenet.in_layers.0.parametrizations.weight.original0', 'flow.flows.1.wavenet.in_layers.0.parametrizations.weight.original1', 'flow.flows.1.wavenet.in_layers.1.parametrizations.weight.original0', 'flow.flows.1.wavenet.in_layers.1.parametrizations.weight.original1', 'flow.flows.1.wavenet.in_layers.2.parametrizations.weight.original0', 'flow.flows.1.wavenet.in_layers.2.parametrizations.weight.original1', 'flow.flows.1.wavenet.in_layers.3.parametrizations.weight.original0', 'flow.flows.1.wavenet.in_layers.3.parametrizations.weight.original1', 'flow.flows.1.wavenet.res_skip_layers.0.parametrizations.weight.original0', 'flow.flows.1.wavenet.res_skip_layers.0.parametrizations.weight.original1', 'flow.flows.1.wavenet.res_skip_layers.1.parametrizations.weight.original0', 'flow.flows.1.wavenet.res_skip_layers.1.parametrizations.weight.original1', 'flow.flows.1.wavenet.res_skip_layers.2.parametrizations.weight.original0', 'flow.flows.1.wavenet.res_skip_layers.2.parametrizations.weight.original1', 'flow.flows.1.wavenet.res_skip_layers.3.parametrizations.weight.original0', 'flow.flows.1.wavenet.res_skip_layers.3.parametrizations.weight.original1', 'flow.flows.2.wavenet.in_layers.0.parametrizations.weight.original0', 'flow.flows.2.wavenet.in_layers.0.parametrizations.weight.original1', 'flow.flows.2.wavenet.in_layers.1.parametrizations.weight.original0', 'flow.flows.2.wavenet.in_layers.1.parametrizations.weight.original1', 'flow.flows.2.wavenet.in_layers.2.parametrizations.weight.original0', 'flow.flows.2.wavenet.in_layers.2.parametrizations.weight.original1', 'flow.flows.2.wavenet.in_layers.3.parametrizations.weight.original0', 'flow.flows.2.wavenet.in_layers.3.parametrizations.weight.original1', 'flow.flows.2.wavenet.res_skip_layers.0.parametrizations.weight.original0', 'flow.flows.2.wavenet.res_skip_layers.0.parametrizations.weight.original1', 'flow.flows.2.wavenet.res_skip_layers.1.parametrizations.weight.original0', 'flow.flows.2.wavenet.res_skip_layers.1.parametrizations.weight.original1', 'flow.flows.2.wavenet.res_skip_layers.2.parametrizations.weight.original0', 'flow.flows.2.wavenet.res_skip_layers.2.parametrizations.weight.original1', 'flow.flows.2.wavenet.res_skip_layers.3.parametrizations.weight.original0', 'flow.flows.2.wavenet.res_skip_layers.3.parametrizations.weight.original1', 'flow.flows.3.wavenet.in_layers.0.parametrizations.weight.original0', 'flow.flows.3.wavenet.in_layers.0.parametrizations.weight.original1', 'flow.flows.3.wavenet.in_layers.1.parametrizations.weight.original0', 'flow.flows.3.wavenet.in_layers.1.parametrizations.weight.original1', 'flow.flows.3.wavenet.in_layers.2.parametrizations.weight.original0', 'flow.flows.3.wavenet.in_layers.2.parametrizations.weight.original1', 'flow.flows.3.wavenet.in_layers.3.parametrizations.weight.original0', 'flow.flows.3.wavenet.in_layers.3.parametrizations.weight.original1', 'flow.flows.3.wavenet.res_skip_layers.0.parametrizations.weight.original0', 'flow.flows.3.wavenet.res_skip_layers.0.parametrizations.weight.original1', 'flow.flows.3.wavenet.res_skip_layers.1.parametrizations.weight.original0', 'flow.flows.3.wavenet.res_skip_layers.1.parametrizations.weight.original1', 'flow.flows.3.wavenet.res_skip_layers.2.parametrizations.weight.original0', 'flow.flows.3.wavenet.res_skip_layers.2.parametrizations.weight.original1', 'flow.flows.3.wavenet.res_skip_layers.3.parametrizations.weight.original0', 'flow.flows.3.wavenet.res_skip_layers.3.parametrizations.weight.original1', 'posterior_encoder.wavenet.in_layers.0.parametrizations.weight.original0', 'posterior_encoder.wavenet.in_layers.0.parametrizations.weight.original1', 'posterior_encoder.wavenet.in_layers.1.parametrizations.weight.original0', 'posterior_encoder.wavenet.in_layers.1.parametrizations.weight.original1', 'posterior_encoder.wavenet.in_layers.10.parametrizations.weight.original0', 'posterior_encoder.wavenet.in_layers.10.parametrizations.weight.original1', 'posterior_encoder.wavenet.in_layers.11.parametrizations.weight.original0', 'posterior_encoder.wavenet.in_layers.11.parametrizations.weight.original1', 'posterior_encoder.wavenet.in_layers.12.parametrizations.weight.original0', 'posterior_encoder.wavenet.in_layers.12.parametrizations.weight.original1', 'posterior_encoder.wavenet.in_layers.13.parametrizations.weight.original0', 'posterior_encoder.wavenet.in_layers.13.parametrizations.weight.original1', 'posterior_encoder.wavenet.in_layers.14.parametrizations.weight.original0', 'posterior_encoder.wavenet.in_layers.14.parametrizations.weight.original1', 'posterior_encoder.wavenet.in_layers.15.parametrizations.weight.original0', 'posterior_encoder.wavenet.in_layers.15.parametrizations.weight.original1', 'posterior_encoder.wavenet.in_layers.2.parametrizations.weight.original0', 'posterior_encoder.wavenet.in_layers.2.parametrizations.weight.original1', 'posterior_encoder.wavenet.in_layers.3.parametrizations.weight.original0', 'posterior_encoder.wavenet.in_layers.3.parametrizations.weight.original1', 'posterior_encoder.wavenet.in_layers.4.parametrizations.weight.original0', 'posterior_encoder.wavenet.in_layers.4.parametrizations.weight.original1', 'posterior_encoder.wavenet.in_layers.5.parametrizations.weight.original0', 'posterior_encoder.wavenet.in_layers.5.parametrizations.weight.original1', 'posterior_encoder.wavenet.in_layers.6.parametrizations.weight.original0', 'posterior_encoder.wavenet.in_layers.6.parametrizations.weight.original1', 'posterior_encoder.wavenet.in_layers.7.parametrizations.weight.original0', 'posterior_encoder.wavenet.in_layers.7.parametrizations.weight.original1', 'posterior_encoder.wavenet.in_layers.8.parametrizations.weight.original0', 'posterior_encoder.wavenet.in_layers.8.parametrizations.weight.original1', 'posterior_encoder.wavenet.in_layers.9.parametrizations.weight.original0', 'posterior_encoder.wavenet.in_layers.9.parametrizations.weight.original1', 'posterior_encoder.wavenet.res_skip_layers.0.parametrizations.weight.original0', 'posterior_encoder.wavenet.res_skip_layers.0.parametrizations.weight.original1', 'posterior_encoder.wavenet.res_skip_layers.1.parametrizations.weight.original0', 'posterior_encoder.wavenet.res_skip_layers.1.parametrizations.weight.original1', 'posterior_encoder.wavenet.res_skip_layers.10.parametrizations.weight.original0', 'posterior_encoder.wavenet.res_skip_layers.10.parametrizations.weight.original1', 'posterior_encoder.wavenet.res_skip_layers.11.parametrizations.weight.original0', 'posterior_encoder.wavenet.res_skip_layers.11.parametrizations.weight.original1', 'posterior_encoder.wavenet.res_skip_layers.12.parametrizations.weight.original0', 'posterior_encoder.wavenet.res_skip_layers.12.parametrizations.weight.original1', 'posterior_encoder.wavenet.res_skip_layers.13.parametrizations.weight.original0', 'posterior_encoder.wavenet.res_skip_layers.13.parametrizations.weight.original1', 'posterior_encoder.wavenet.res_skip_layers.14.parametrizations.weight.original0', 'posterior_encoder.wavenet.res_skip_layers.14.parametrizations.weight.original1', 'posterior_encoder.wavenet.res_skip_layers.15.parametrizations.weight.original0', 'posterior_encoder.wavenet.res_skip_layers.15.parametrizations.weight.original1', 'posterior_encoder.wavenet.res_skip_layers.2.parametrizations.weight.original0', 'posterior_encoder.wavenet.res_skip_layers.2.parametrizations.weight.original1', 'posterior_encoder.wavenet.res_skip_layers.3.parametrizations.weight.original0', 'posterior_encoder.wavenet.res_skip_layers.3.parametrizations.weight.original1', 'posterior_encoder.wavenet.res_skip_layers.4.parametrizations.weight.original0', 'posterior_encoder.wavenet.res_skip_layers.4.parametrizations.weight.original1', 'posterior_encoder.wavenet.res_skip_layers.5.parametrizations.weight.original0', 'posterior_encoder.wavenet.res_skip_layers.5.parametrizations.weight.original1', 'posterior_encoder.wavenet.res_skip_layers.6.parametrizations.weight.original0', 'posterior_encoder.wavenet.res_skip_layers.6.parametrizations.weight.original1', 'posterior_encoder.wavenet.res_skip_layers.7.parametrizations.weight.original0', 'posterior_encoder.wavenet.res_skip_layers.7.parametrizations.weight.original1', 'posterior_encoder.wavenet.res_skip_layers.8.parametrizations.weight.original0', 'posterior_encoder.wavenet.res_skip_layers.8.parametrizations.weight.original1', 'posterior_encoder.wavenet.res_skip_layers.9.parametrizations.weight.original0', 'posterior_encoder.wavenet.res_skip_layers.9.parametrizations.weight.original1']\n", + "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "from VitsModelSplit.dataset_features_collector import FeaturesCollectionDataset\n", + "\n", + "dataset_dir = '/content/drive/MyDrive/FeaturesCollectionDataset'\n", + "full_generation_sample_index = 0\n", + "full_generation_dataset = FeaturesCollectionDataset(dataset_dir = os.path.join(dataset_dir,'full_generation'),\n", + " device = model_new.device\n", + " )\n", + "full_generation_sample = full_generation_dataset[full_generation_sample_index]\n", + "\n", + "set_seed(42)\n", + "with torch.no_grad():\n", + " full_generation =model_new(\n", + " input_ids =full_generation_sample[\"input_ids\"],\n", + " attention_mask=full_generation_sample[\"attention_mask\"],\n", + " speaker_id=full_generation_sample[\"speaker_id\"]\n", + " )\n", + " full_generation_waveform = full_generation.waveform.cpu().numpy().reshape(-1)\n", + "\n", + "\n", + "Audio(full_generation_waveform, rate=model_new.config.sampling_rate)" + ], + "metadata": { + "id": "I9YkPdvXCOnr", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 76 + }, + "outputId": "469f1ec9-4159-44ad-b13e-98ce019d41b4" + }, + "execution_count": 12, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "\n", + " \n", + " " + ] + }, + "metadata": {}, + "execution_count": 12 + } + ] + } + ] +} \ No newline at end of file