{"cells":[{"cell_type":"markdown","metadata":{"id":"TC3XkMetGWtK"},"source":["# Neural Amp Modeler [REVERSED] - Model Training Notebook\n","🔶**Before you run**🔶\n","\n","Make sure to get a GPU! (From the upper-left menu, click Runtime->Change runtime type->Select \"GPU\" from the \"Hardware accelerator dropdown menu)"]},{"cell_type":"markdown","metadata":{"id":"5CQleTk7GJV8"},"source":["## Step 1: Get data\n","* **Download the reamp signal.** Here: [input.wav](https://drive.google.com/file/d/1KbaS4oXXNEuh2aCPLwKrPdf5KFOjda8G/view?usp=drive_link).\n","* **Reamp your gear.** Then reamp the gear you want to model using it. Save that reamp as **\"output.wav\"**. *Note: Use 48kHz, 24-bit, mono.* For other sample rates, use [the CLI trainer](https://github.com/sdatkinson/neural-amp-modeler).\n","* **Upload your files.** Upload `input.wav` and your `output.wav` by clicking the Folder icon on the left ⬅ and then clicking the upload icon or by dragging the files into the panel."]},{"cell_type":"code","source":["from google.colab import drive\n","drive.mount('/content/drive')"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"uZxLWFQfBK5b","executionInfo":{"status":"ok","timestamp":1729345843025,"user_tz":-120,"elapsed":32321,"user":{"displayName":"Rickard","userId":"13996032449383725839"}},"outputId":"e6b34395-29c1-44f4-dc4a-94658fc05292"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Mounted at /content/drive\n"]}]},{"cell_type":"markdown","metadata":{"id":"7tRCyI_YjZjj"},"source":["## Step 2: Train!\n","Configure your training run below, then hit the Play button to start training!\n","\n","🕙NOTE: At default settings, training will take about 10 minutes.🕙"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"zrXbQY7vjZjk","cellView":"form"},"outputs":[],"source":["# Hi there! This is the code that makes this notebook work. Feel free to mess around\n","# with it :)\n","\n","try:\n","    import nam\n","except ImportError as e:\n","    print(\"Installing NAM into Colab. This should take a couple seconds.\")\n","    # Check what we're starting with (Issue 399)\n","    !if [ ! -d logs ]; then mkdir logs; fi\n","    !pip list > logs/packages.log\n","    # !pip install neural-amp-modeler==0.10 >& logs/install.log\n","    # Hint: use the next line instead for the very latest!\n","    !pip install git+https://github.com/38github/neural-amp-modeler\n","\n","from typing import Optional\n","\n","from nam.train.colab import run\n","from nam.models.metadata import GearType, ToneType, UserMetadata\n","\n","%load_ext tensorboard\n","\n","from functools import partial\n","\n","import ipywidgets as widgets\n","\n","# NOTE: Enums need to be handled carefully since the values need to be supplied literally here!\n","\n","#@markdown # Training parameters\n","epochs = 500 #@param {type: \"number\"}\n","architecture = \"standard\"  #@param [\"standard\", \"lite\", \"feather\", \"nano\"] {type: \"string\"}\n","latency_samples = \"0\"  #@param {type: \"string\"}\n","ignore_checks = False #@param {type: \"boolean\"}\n","\n","#@markdown # Metadata\n","use_metadata = True #@param {type: \"boolean\"}\n","name = \"\" #@param {type:\"string\"}\n","modeled_by = \" / R Gerthsson\" #@param {type:\"string\"}\n","gear_make = \"\" #@param {type:\"string\"}\n","gear_model = \"\" #@param {type:\"string\"}\n","gear_type = \"amp\" #@param [\"amp\", \"pedal\", \"pedal_amp\", \"amp_cab\", \"amp_pedal_cab\", \"preamp\", \"studio\"] {type:\"string\"}\n","tone_type = \"hi_gain\" #@param [\"clean\", \"overdrive\", \"crunch\", \"hi_gain\", \"fuzz\"] {type:\"string\"}\n","# DRY: \"(optional)\" used below in _parse_level_dbu\n","reamp_default_value = \"(optional)\"\n","reamp_send_level = \"(optional)\" #@param {type:\"string\"}\n","reamp_return_level = \"(optional)\" #@param {type:\"string\"}\n","#@markdown _For more information on measuring your reamp send and return calibration levels, see [the documentation](https://neural-amp-modeler.readthedocs.io/en/stable/tutorials/calibration.html)._\n","\n","# A few helper functions to make sense of the values provided above.\n","def _verbose_enum(E, val):\n","    try:\n","        return E(val)\n","    except ValueError as e:\n","        raise ValueError(\n","            str(e)\n","            + \"\\nValid choices are: \"\n","            + \", \".join(list(x.value for x in E))\n","        )\n","\n","def _parse_latency(ls: str):\n","    if ls.lower() == \"auto\":\n","        return None\n","    try:\n","        return int(ls)\n","    except ValueError as e:\n","        raise ValueError(\n","            f\"Invalid value for latency {ls} was given. Either use 'auto' or provide \"\n","            f\"the reamp latency, in samples.\\nOriginal exception:\\n\\n{e}\"\n","        )\n","\n","def _parse_level_dbu(value: str) -> Optional[float]:\n","    if value in {\"\", reamp_default_value}:\n","        return None\n","    try:\n","        return float(value)\n","    except ValueError as e:\n","        raise ValueError(\n","            f\"Error parsing provided calibration level '{value}'. Either specify a \"\n","            f\"number or leave blank.\\n\\nOriginal exception: {e}\"\n","        )\n","\n","if not use_metadata:\n","    print(\"Metadata will be skipped\")\n","    user_metadata = None\n","else:\n","    print(\"Parsing user-provided metadata...\")\n","    user_metadata = UserMetadata(\n","        name=name,\n","        modeled_by=modeled_by,\n","        gear_make=gear_make,\n","        gear_model=gear_model,\n","        gear_type=_verbose_enum(GearType, gear_type.lower()),\n","        tone_type=_verbose_enum(ToneType, tone_type.lower()),\n","        input_level_dbu=_parse_level_dbu(reamp_send_level),\n","        output_level_dbu=_parse_level_dbu(reamp_return_level),\n","    )\n","\n","%tensorboard --logdir /content/lightning_logs\n","run(\n","    epochs=epochs,\n","    architecture=architecture,\n","    ignore_checks=ignore_checks,\n","    user_metadata=user_metadata,\n","    delay=_parse_latency(latency_samples)\n",")"]},{"cell_type":"markdown","metadata":{"id":"823KJ_L0Rchp"},"source":["## Step 3: Check the results and download your model\n","We're done!\n","\n","Have a look at the plot above to see how your model compares to the real gear you're modeling.\n","Hopefully it looks good!\n","Go to the file browser on the left panel ⬅ and download `model.nam` from the `exported_model` directory (you may need to hit the refresh button).\n","\n","# 🎸 **ENJOY!** 🎸"]}],"metadata":{"accelerator":"GPU","colab":{"provenance":[]},"gpuClass":"standard","kernelspec":{"display_name":"nam","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.10.6"},"orig_nbformat":4,"vscode":{"interpreter":{"hash":"920df60c69944ba95f8c12adb41fedfdc8090c370a20d39253c7705973dd37db"}}},"nbformat":4,"nbformat_minor":0}