{ "cells": [ { "cell_type": "markdown", "metadata": { "id": "view-in-github", "colab_type": "text" }, "source": [ "\"Open" ] }, { "cell_type": "markdown", "source": [ "# New Section" ], "metadata": { "id": "jbe_aWYkjWRH" }, "id": "jbe_aWYkjWRH" }, { "cell_type": "code", "execution_count": 2, "id": "dd70762d", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "dd70762d", "outputId": "499681b1-46d6-4f21-b3b8-3a3348f6765b" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Cloning into 'denoising-historical-recordings'...\n", "remote: Enumerating objects: 177, done.\u001b[K\n", "remote: Counting objects: 100% (177/177), done.\u001b[K\n", "remote: Compressing objects: 100% (153/153), done.\u001b[K\n", "remote: Total 177 (delta 63), reused 99 (delta 16), pack-reused 0\u001b[K\n", "Receiving objects: 100% (177/177), 97.29 KiB | 4.86 MiB/s, done.\n", "Resolving deltas: 100% (63/63), done.\n" ] } ], "source": [ "#download the files\n", "! git clone https://github.com/eloimoliner/denoising-historical-recordings.git\n", "! wget https://github.com/eloimoliner/denoising-historical-recordings/releases/download/v0.0/checkpoint.zip\n", "! unzip checkpoint.zip -d denoising-historical-recordings/experiments/trained_model/" ] }, { "cell_type": "code", "source": [ "\n", "%cd denoising-historical-recordings" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "HmHRpa5eloy2", "outputId": "34af882d-8fb7-4b2a-dccd-50e328e0ab90" }, "id": "HmHRpa5eloy2", "execution_count": 18, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "/content/denoising-historical-recordings\n" ] } ] }, { "cell_type": "code", "source": [ "" ], "metadata": { "id": "gvd6KZkTlyhR" }, "id": "gvd6KZkTlyhR", "execution_count": 12, "outputs": [] }, { "cell_type": "code", "source": [ "#install dependencies\n", "! pip install hydra-core==0.11.3" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "nmic9hVzmSj6", "outputId": "c549f0d1-9e5c-4445-ecd4-702697535011" }, "id": "nmic9hVzmSj6", "execution_count": 15, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Collecting hydra-core==0.11.3\n", " Downloading hydra_core-0.11.3-py3-none-any.whl (72 kB)\n", "\u001b[?25l\r\u001b[K |████▌ | 10 kB 19.6 MB/s eta 0:00:01\r\u001b[K |█████████ | 20 kB 12.0 MB/s eta 0:00:01\r\u001b[K |█████████████▋ | 30 kB 8.9 MB/s eta 0:00:01\r\u001b[K |██████████████████▏ | 40 kB 7.9 MB/s eta 0:00:01\r\u001b[K |██████████████████████▊ | 51 kB 5.3 MB/s eta 0:00:01\r\u001b[K |███████████████████████████▎ | 61 kB 5.4 MB/s eta 0:00:01\r\u001b[K |███████████████████████████████▉| 71 kB 5.7 MB/s eta 0:00:01\r\u001b[K |████████████████████████████████| 72 kB 372 kB/s \n", "\u001b[?25hCollecting omegaconf<1.5,>=1.4\n", " Downloading omegaconf-1.4.1-py3-none-any.whl (14 kB)\n", "Requirement already satisfied: six in /usr/local/lib/python3.7/site-packages (from omegaconf<1.5,>=1.4->hydra-core==0.11.3) (1.15.0)\n", "Collecting PyYAML\n", " Downloading PyYAML-6.0-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl (596 kB)\n", "\u001b[K |████████████████████████████████| 596 kB 39.4 MB/s \n", "\u001b[?25hInstalling collected packages: PyYAML, omegaconf, hydra-core\n", "Successfully installed PyYAML-6.0 hydra-core-0.11.3 omegaconf-1.4.1\n" ] } ] }, { "cell_type": "code", "source": [ "import unet\n", "import tensorflow as tf\n", "import soundfile as sf\n", "import numpy as np\n", "from tqdm import tqdm\n", "import scipy.signal\n", "import hydra\n", "import os" ], "metadata": { "id": "TQBDTmO4mUBx" }, "id": "TQBDTmO4mUBx", "execution_count": 17, "outputs": [] }, { "cell_type": "code", "source": [ "#workaround to load hydra conf file\n", "import yaml\n", "from pathlib import Path\n", "args = yaml.safe_load(Path('conf/conf.yaml').read_text())\n", "class dotdict(dict):\n", " \"\"\"dot.notation access to dictionary attributes\"\"\"\n", " __getattr__ = dict.get\n", " __setattr__ = dict.__setitem__\n", " __delattr__ = dict.__delitem__\n", "args=dotdict(args)\n", "unet_args=dotdict(args.unet)" ], "metadata": { "id": "yMI9sIUYo9Lp" }, "id": "yMI9sIUYo9Lp", "execution_count": 62, "outputs": [] }, { "cell_type": "code", "source": [ "path_experiment=str(args.path_experiment)\n", "\n", "unet_model = unet.build_model_denoise(unet_args=unet_args)\n", "\n", "ckpt=os.path.join(\"/content/denoising-historical-recordings\",path_experiment, 'checkpoint')\n", "unet_model.load_weights(ckpt)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "cbdPyEpAp7s0", "outputId": "63df20d2-1c00-41a5-c8fc-a6cdcfb57d08" }, "id": "cbdPyEpAp7s0", "execution_count": 67, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "" ] }, "metadata": {}, "execution_count": 67 } ] }, { "cell_type": "code", "source": [ "def do_stft(noisy):\n", " \n", " window_fn = tf.signal.hamming_window\n", "\n", " win_size=args.stft[\"win_size\"]\n", " hop_size=args.stft[\"hop_size\"]\n", "\n", " \n", " stft_signal_noisy=tf.signal.stft(noisy,frame_length=win_size, window_fn=window_fn, frame_step=hop_size, pad_end=True)\n", " stft_noisy_stacked=tf.stack( values=[tf.math.real(stft_signal_noisy), tf.math.imag(stft_signal_noisy)], axis=-1)\n", "\n", " return stft_noisy_stacked\n", "\n", "def do_istft(data):\n", " \n", " window_fn = tf.signal.hamming_window\n", "\n", " win_size=args.stft[\"win_size\"]\n", " hop_size=args.stft[\"hop_size\"]\n", "\n", " inv_window_fn=tf.signal.inverse_stft_window_fn(hop_size, forward_window_fn=window_fn)\n", "\n", " pred_cpx=data[...,0] + 1j * data[...,1]\n", " pred_time=tf.signal.inverse_stft(pred_cpx, win_size, hop_size, window_fn=inv_window_fn)\n", " return pred_time\n" ], "metadata": { "id": "iDJGN-1_taXR" }, "id": "iDJGN-1_taXR", "execution_count": 79, "outputs": [] }, { "cell_type": "code", "source": [ "def denoise_audio(audio):\n", "\n", " data, samplerate = sf.read(audio)\n", " print(data.dtype)\n", " #Stereo to mono\n", " if len(data.shape)>1:\n", " data=np.mean(data,axis=1)\n", " \n", " if samplerate!=44100: \n", " print(\"Resampling\")\n", " \n", " data=scipy.signal.resample(data, int((44100 / samplerate )*len(data))+1) \n", " \n", " \n", " \n", " segment_size=44100*5 #20s segments\n", "\n", " length_data=len(data)\n", " overlapsize=2048 #samples (46 ms)\n", " window=np.hanning(2*overlapsize)\n", " window_right=window[overlapsize::]\n", " window_left=window[0:overlapsize]\n", " audio_finished=False\n", " pointer=0\n", " denoised_data=np.zeros(shape=(len(data),))\n", " residual_noise=np.zeros(shape=(len(data),))\n", " numchunks=int(np.ceil(length_data/segment_size))\n", " \n", " for i in tqdm(range(numchunks)):\n", " if pointer+segment_size\n", " \n", " Upload widget is only available when the cell has been executed in the\n", " current browser session. Please rerun this cell to enable.\n", " \n", " " ], "text/plain": [ "" ] }, "metadata": {} }, { "output_type": "stream", "name": "stdout", "text": [ "Saving Carmen-Habanera_(Love_is_Like_a_Woo_-_Marguerite_D'Alvarez_noisy_input.wav to Carmen-Habanera_(Love_is_Like_a_Woo_-_Marguerite_D'Alvarez_noisy_input.wav\n" ] } ] }, { "cell_type": "code", "source": [ "for fn in uploaded.keys():\n", " print('Denoising uploaded file \"{name}\"'.format(\n", " name=fn))\n", " denoise_data=denoise_audio(fn)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "0po6zpvrylc2", "outputId": "0d2b228e-dad8-40f8-f10a-118ea115180d" }, "id": "0po6zpvrylc2", "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "\r 0%| | 0/41 [00:00