588 lines
31 KiB
Plaintext
588 lines
31 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"colab": {
|
|
"base_uri": "https://localhost:8080/"
|
|
},
|
|
"id": "-s-0Go_idJSV",
|
|
"outputId": "998d34fd-9d21-4854-da2a-867e14600624"
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Collecting python-telegram-bot==13.7\n",
|
|
" Downloading python_telegram_bot-13.7-py3-none-any.whl (490 kB)\n",
|
|
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m490.1/490.1 kB\u001b[0m \u001b[31m3.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
|
"\u001b[?25hRequirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from python-telegram-bot==13.7) (2024.2.2)\n",
|
|
"Requirement already satisfied: tornado>=6.1 in /usr/local/lib/python3.10/dist-packages (from python-telegram-bot==13.7) (6.3.3)\n",
|
|
"Collecting APScheduler==3.6.3 (from python-telegram-bot==13.7)\n",
|
|
" Downloading APScheduler-3.6.3-py2.py3-none-any.whl (58 kB)\n",
|
|
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.9/58.9 kB\u001b[0m \u001b[31m5.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
|
"\u001b[?25hRequirement already satisfied: pytz>=2018.6 in /usr/local/lib/python3.10/dist-packages (from python-telegram-bot==13.7) (2023.4)\n",
|
|
"Collecting cachetools==4.2.2 (from python-telegram-bot==13.7)\n",
|
|
" Downloading cachetools-4.2.2-py3-none-any.whl (11 kB)\n",
|
|
"Requirement already satisfied: setuptools>=0.7 in /usr/local/lib/python3.10/dist-packages (from APScheduler==3.6.3->python-telegram-bot==13.7) (67.7.2)\n",
|
|
"Requirement already satisfied: six>=1.4.0 in /usr/local/lib/python3.10/dist-packages (from APScheduler==3.6.3->python-telegram-bot==13.7) (1.16.0)\n",
|
|
"Requirement already satisfied: tzlocal>=1.2 in /usr/local/lib/python3.10/dist-packages (from APScheduler==3.6.3->python-telegram-bot==13.7) (5.2)\n",
|
|
"Installing collected packages: cachetools, APScheduler, python-telegram-bot\n",
|
|
" Attempting uninstall: cachetools\n",
|
|
" Found existing installation: cachetools 5.3.3\n",
|
|
" Uninstalling cachetools-5.3.3:\n",
|
|
" Successfully uninstalled cachetools-5.3.3\n",
|
|
"Successfully installed APScheduler-3.6.3 cachetools-4.2.2 python-telegram-bot-13.7\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"pip install python-telegram-bot==13.7"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"colab": {
|
|
"base_uri": "https://localhost:8080/"
|
|
},
|
|
"id": "SnIbxiLxpsWI",
|
|
"outputId": "336a0a96-4a81-4ed3-ce0a-8018705c85da"
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Collecting openai-whisper\n",
|
|
" Downloading openai-whisper-20231117.tar.gz (798 kB)\n",
|
|
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m798.6/798.6 kB\u001b[0m \u001b[31m5.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
|
"\u001b[?25h Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
|
|
" Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
|
|
" Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
|
|
"Requirement already satisfied: triton<3,>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from openai-whisper) (2.2.0)\n",
|
|
"Requirement already satisfied: numba in /usr/local/lib/python3.10/dist-packages (from openai-whisper) (0.58.1)\n",
|
|
"Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from openai-whisper) (1.25.2)\n",
|
|
"Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (from openai-whisper) (2.2.1+cu121)\n",
|
|
"Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from openai-whisper) (4.66.2)\n",
|
|
"Requirement already satisfied: more-itertools in /usr/local/lib/python3.10/dist-packages (from openai-whisper) (10.1.0)\n",
|
|
"Collecting tiktoken (from openai-whisper)\n",
|
|
" Downloading tiktoken-0.6.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.8 MB)\n",
|
|
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.8/1.8 MB\u001b[0m \u001b[31m22.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
|
"\u001b[?25hRequirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from triton<3,>=2.0.0->openai-whisper) (3.13.4)\n",
|
|
"Requirement already satisfied: llvmlite<0.42,>=0.41.0dev0 in /usr/local/lib/python3.10/dist-packages (from numba->openai-whisper) (0.41.1)\n",
|
|
"Requirement already satisfied: regex>=2022.1.18 in /usr/local/lib/python3.10/dist-packages (from tiktoken->openai-whisper) (2023.12.25)\n",
|
|
"Requirement already satisfied: requests>=2.26.0 in /usr/local/lib/python3.10/dist-packages (from tiktoken->openai-whisper) (2.31.0)\n",
|
|
"Requirement already satisfied: typing-extensions>=4.8.0 in /usr/local/lib/python3.10/dist-packages (from torch->openai-whisper) (4.11.0)\n",
|
|
"Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch->openai-whisper) (1.12)\n",
|
|
"Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch->openai-whisper) (3.3)\n",
|
|
"Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch->openai-whisper) (3.1.3)\n",
|
|
"Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch->openai-whisper) (2023.6.0)\n",
|
|
"Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch->openai-whisper)\n",
|
|
" Using cached nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)\n",
|
|
"Collecting nvidia-cuda-runtime-cu12==12.1.105 (from torch->openai-whisper)\n",
|
|
" Using cached nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)\n",
|
|
"Collecting nvidia-cuda-cupti-cu12==12.1.105 (from torch->openai-whisper)\n",
|
|
" Using cached nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)\n",
|
|
"Collecting nvidia-cudnn-cu12==8.9.2.26 (from torch->openai-whisper)\n",
|
|
" Using cached nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)\n",
|
|
"Collecting nvidia-cublas-cu12==12.1.3.1 (from torch->openai-whisper)\n",
|
|
" Using cached nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)\n",
|
|
"Collecting nvidia-cufft-cu12==11.0.2.54 (from torch->openai-whisper)\n",
|
|
" Using cached nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)\n",
|
|
"Collecting nvidia-curand-cu12==10.3.2.106 (from torch->openai-whisper)\n",
|
|
" Using cached nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)\n",
|
|
"Collecting nvidia-cusolver-cu12==11.4.5.107 (from torch->openai-whisper)\n",
|
|
" Using cached nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)\n",
|
|
"Collecting nvidia-cusparse-cu12==12.1.0.106 (from torch->openai-whisper)\n",
|
|
" Using cached nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)\n",
|
|
"Collecting nvidia-nccl-cu12==2.19.3 (from torch->openai-whisper)\n",
|
|
" Using cached nvidia_nccl_cu12-2.19.3-py3-none-manylinux1_x86_64.whl (166.0 MB)\n",
|
|
"Collecting nvidia-nvtx-cu12==12.1.105 (from torch->openai-whisper)\n",
|
|
" Using cached nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)\n",
|
|
"Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch->openai-whisper)\n",
|
|
" Using cached nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (21.1 MB)\n",
|
|
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.26.0->tiktoken->openai-whisper) (3.3.2)\n",
|
|
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.26.0->tiktoken->openai-whisper) (3.7)\n",
|
|
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.26.0->tiktoken->openai-whisper) (2.0.7)\n",
|
|
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.26.0->tiktoken->openai-whisper) (2024.2.2)\n",
|
|
"Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch->openai-whisper) (2.1.5)\n",
|
|
"Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch->openai-whisper) (1.3.0)\n",
|
|
"Building wheels for collected packages: openai-whisper\n",
|
|
" Building wheel for openai-whisper (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
|
|
" Created wheel for openai-whisper: filename=openai_whisper-20231117-py3-none-any.whl size=801358 sha256=e35ec844abfadc2b26e9cb01404f2e6b85a1048b6d8afb437958914d59bd983d\n",
|
|
" Stored in directory: /root/.cache/pip/wheels/d0/85/e1/9361b4cbea7dd4b7f6702fa4c3afc94877952eeb2b62f45f56\n",
|
|
"Successfully built openai-whisper\n",
|
|
"Installing collected packages: nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, tiktoken, nvidia-cusparse-cu12, nvidia-cudnn-cu12, nvidia-cusolver-cu12, openai-whisper\n",
|
|
"Successfully installed nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.19.3 nvidia-nvjitlink-cu12-12.4.127 nvidia-nvtx-cu12-12.1.105 openai-whisper-20231117 tiktoken-0.6.0\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"pip install -U openai-whisper"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"colab": {
|
|
"base_uri": "https://localhost:8080/"
|
|
},
|
|
"id": "FH9pRMGkps08",
|
|
"outputId": "b6487d28-bdac-40ff-e71e-b27502c01cdc"
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (2.2.1+cu121)\n",
|
|
"Collecting torch\n",
|
|
" Downloading torch-2.2.2-cp310-cp310-manylinux1_x86_64.whl (755.5 MB)\n",
|
|
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m755.5/755.5 MB\u001b[0m \u001b[31m1.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
|
"\u001b[?25hRequirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch) (3.13.4)\n",
|
|
"Requirement already satisfied: typing-extensions>=4.8.0 in /usr/local/lib/python3.10/dist-packages (from torch) (4.11.0)\n",
|
|
"Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch) (1.12)\n",
|
|
"Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch) (3.3)\n",
|
|
"Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch) (3.1.3)\n",
|
|
"Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch) (2023.6.0)\n",
|
|
"Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch) (12.1.105)\n",
|
|
"Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch) (12.1.105)\n",
|
|
"Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch) (12.1.105)\n",
|
|
"Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /usr/local/lib/python3.10/dist-packages (from torch) (8.9.2.26)\n",
|
|
"Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.10/dist-packages (from torch) (12.1.3.1)\n",
|
|
"Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.10/dist-packages (from torch) (11.0.2.54)\n",
|
|
"Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.10/dist-packages (from torch) (10.3.2.106)\n",
|
|
"Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.10/dist-packages (from torch) (11.4.5.107)\n",
|
|
"Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.10/dist-packages (from torch) (12.1.0.106)\n",
|
|
"Requirement already satisfied: nvidia-nccl-cu12==2.19.3 in /usr/local/lib/python3.10/dist-packages (from torch) (2.19.3)\n",
|
|
"Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch) (12.1.105)\n",
|
|
"Requirement already satisfied: triton==2.2.0 in /usr/local/lib/python3.10/dist-packages (from torch) (2.2.0)\n",
|
|
"Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.10/dist-packages (from nvidia-cusolver-cu12==11.4.5.107->torch) (12.4.127)\n",
|
|
"Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch) (2.1.5)\n",
|
|
"Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch) (1.3.0)\n",
|
|
"Installing collected packages: torch\n",
|
|
" Attempting uninstall: torch\n",
|
|
" Found existing installation: torch 2.2.1+cu121\n",
|
|
" Uninstalling torch-2.2.1+cu121:\n",
|
|
" Successfully uninstalled torch-2.2.1+cu121\n",
|
|
"\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
|
|
"torchaudio 2.2.1+cu121 requires torch==2.2.1, but you have torch 2.2.2 which is incompatible.\n",
|
|
"torchtext 0.17.1 requires torch==2.2.1, but you have torch 2.2.2 which is incompatible.\n",
|
|
"torchvision 0.17.1+cu121 requires torch==2.2.1, but you have torch 2.2.2 which is incompatible.\u001b[0m\u001b[31m\n",
|
|
"\u001b[0mSuccessfully installed torch-2.2.2\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"pip install --upgrade torch"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"id": "SCUSLgFAc7Z4"
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"import librosa\n",
|
|
"import librosa.display\n",
|
|
"import pandas as pd\n",
|
|
"import os\n",
|
|
"import numpy as np\n",
|
|
"import torch\n",
|
|
"import whisper\n",
|
|
"import requests\n",
|
|
"import time\n",
|
|
"np.random.seed(0)\n",
|
|
"from joblib import load\n",
|
|
"from scipy.fftpack import dct\n",
|
|
"from telegram.ext import Updater, MessageHandler, Filters"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"id": "jzQaNFgedBmu"
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Load model yang telah dilatih\n",
|
|
"model = load('/content/drive/MyDrive/Skripsi/rbf/new_user_linear.pkl')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"id": "sh0-ovkleZS0"
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Fungsi pre-emphasis\n",
|
|
"def pre_emphasis(signal, coefficient=0.97):\n",
|
|
" return np.append(signal[0], signal[1:] - coefficient * signal[:-1])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"id": "HeISpxGTebIs"
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Fungsi framing\n",
|
|
"def framing(signal, sample_rate, frame_length=0.025, frame_step=0.010):\n",
|
|
" nsamples_signal = len(signal)\n",
|
|
" nsamples_frame = int(round(frame_length * sample_rate))\n",
|
|
" nsamples_stride = int(round(frame_step * sample_rate))\n",
|
|
" n_frames = int(np.ceil((nsamples_signal - nsamples_frame) / nsamples_stride) + 1)\n",
|
|
" nsamples_padding = ((n_frames - 1) * nsamples_stride + nsamples_frame) - nsamples_signal\n",
|
|
" z = np.zeros(nsamples_padding)\n",
|
|
" signal = np.append(signal, z)\n",
|
|
" frames = np.empty((n_frames, nsamples_frame))\n",
|
|
" for i in range(n_frames):\n",
|
|
" left = i * nsamples_stride\n",
|
|
" right = left + nsamples_frame\n",
|
|
" frame = signal[left:right]\n",
|
|
" frames[i] = frame\n",
|
|
" return frames"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"id": "t24vLFANedWf"
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Fungsi untuk mengekstrak fitur MFCC dari file audio\n",
|
|
"def extract_mfcc(audio_file, sr=44100, frame_length=0.025, frame_step=0.010, nfilt=40, num_ceps=12):\n",
|
|
" y, _ = librosa.load(audio_file, sr=sr)\n",
|
|
"\n",
|
|
" # Normalize\n",
|
|
" y_norm = librosa.util.normalize(y)\n",
|
|
"\n",
|
|
" # Pre-emphasis\n",
|
|
" y_pre_emphasis = pre_emphasis(y_norm)\n",
|
|
"\n",
|
|
" # Framing\n",
|
|
" frames = framing(y_pre_emphasis, sr, frame_length, frame_step)\n",
|
|
"\n",
|
|
" # Hamming window\n",
|
|
" frames *= np.hanning(len(frames[0]))\n",
|
|
"\n",
|
|
" # FFT\n",
|
|
" NFFT = 512\n",
|
|
" mag_frames = np.absolute(np.fft.rfft(frames, NFFT))\n",
|
|
" pow_frames = ((1.0 / NFFT) * ((mag_frames) ** 2))\n",
|
|
"\n",
|
|
" # Mel filter bank\n",
|
|
" low_freq_mel = 0\n",
|
|
" high_freq_mel = (2595 * np.log10(1 + (sr / 2) / 700))\n",
|
|
" mel_points = np.linspace(low_freq_mel, high_freq_mel, nfilt + 2)\n",
|
|
" hz_points = (700 * (10**(mel_points / 2595) - 1))\n",
|
|
" bin = np.floor((NFFT + 1) * hz_points / sr)\n",
|
|
"\n",
|
|
" fbank = np.zeros((nfilt, int(np.floor(NFFT / 2 + 1))))\n",
|
|
" for m in range(1, nfilt + 1):\n",
|
|
" f_m_minus = int(bin[m - 1])\n",
|
|
" f_m = int(bin[m])\n",
|
|
" f_m_plus = int(bin[m + 1])\n",
|
|
" for k in range(f_m_minus, f_m):\n",
|
|
" fbank[m - 1, k] = (k - bin[m - 1]) / (bin[m] - bin[m - 1])\n",
|
|
" for k in range(f_m, f_m_plus):\n",
|
|
" fbank[m - 1, k] = (bin[m + 1] - k) / (bin[m + 1] - bin[m])\n",
|
|
"\n",
|
|
" filter_banks = np.dot(pow_frames, fbank.T)\n",
|
|
" filter_banks = np.where(filter_banks == 0, np.finfo(float).eps, filter_banks)\n",
|
|
" filter_banks = 20 * np.log10(filter_banks)\n",
|
|
"\n",
|
|
" # Discrete Cosine Transform (DCT) for MFCC\n",
|
|
" mfcc = dct(filter_banks, type=2, axis=1, norm='ortho')[:, 1:(num_ceps + 1)]\n",
|
|
"\n",
|
|
" return np.mean(mfcc, axis=0)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"id": "3l8j6nW2_gRB"
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"def send_command_to_firebase(label):\n",
|
|
" # Firebase RTDB path untuk setiap lampu\n",
|
|
" paths = {\n",
|
|
" \"Depan Menyala\": \"/DEPAN\",\n",
|
|
" \"Depan Mati\": \"/DEPAN\",\n",
|
|
" \"Samping Menyala\": \"/SAMPING\",\n",
|
|
" \"Samping Mati\": \"/SAMPING\",\n",
|
|
" \"Tengah Menyala\": \"/TENGAH\",\n",
|
|
" \"Tengah Mati\": \"/TENGAH\"\n",
|
|
" }\n",
|
|
"\n",
|
|
" # Firebase value untuk setiap label\n",
|
|
" values = {\n",
|
|
" \"Depan Menyala\": \"1\",\n",
|
|
" \"Depan Mati\": \"0\",\n",
|
|
" \"Samping Menyala\": \"1\",\n",
|
|
" \"Samping Mati\": \"0\",\n",
|
|
" \"Tengah Menyala\": \"1\",\n",
|
|
" \"Tengah Mati\": \"0\"\n",
|
|
" }\n",
|
|
"\n",
|
|
" # Mengirim perintah ke Firebase\n",
|
|
" if label in paths:\n",
|
|
" path = paths[label]\n",
|
|
" value = values[label]\n",
|
|
" firebase_url = f\"https://smart-home-e64ae-default-rtdb.firebaseio.com/{path}.json?auth=AIzaSyCmquF32M-zZDpW_Hswg9ZvREgikmteJMY\"\n",
|
|
" headers = {'Content-type': 'application/json'}\n",
|
|
" response = requests.put(firebase_url, headers=headers, json=value)\n",
|
|
" if response.status_code == 200:\n",
|
|
" print(f\"Firebase update successful for {label}\")\n",
|
|
" else:\n",
|
|
" print(f\"Firebase update failed for {label}\")\n",
|
|
" else:\n",
|
|
" print(f\"Label {label} tidak valid\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"id": "-E17U5INqFBS"
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Load Whisper model\n",
|
|
"model_m = whisper.load_model('medium')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"id": "I4zG7F7-d9Zw"
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"def voice_message_handler(update, context):\n",
|
|
" # Mendapatkan file audio dari pesan suara\n",
|
|
" file_id = update.message.voice.file_id\n",
|
|
" new_file = context.bot.get_file(file_id)\n",
|
|
" file_path = new_file.download()\n",
|
|
"\n",
|
|
" # Ekstraksi fitur MFCC dari file audio\n",
|
|
" mfcc_features = extract_mfcc(file_path)\n",
|
|
"\n",
|
|
" # Reshape MFCC features for prediction\n",
|
|
" X_testing = mfcc_features.reshape(1, -1)\n",
|
|
"\n",
|
|
" # Predict User for the testing data using the trained model\n",
|
|
" start_time = time.time()\n",
|
|
" y_pred_user = model.predict(X_testing)\n",
|
|
" user_prediction_time = (time.time() - start_time) * 1000\n",
|
|
"\n",
|
|
" # Speech to text Label\n",
|
|
" start_time = time.time()\n",
|
|
" translation = model_m.transcribe(file_path, language='id', fp16=False)['text']\n",
|
|
" translation_time = (time.time() - start_time) * 1000\n",
|
|
"\n",
|
|
" # Check if the predicted label is within your expected range of labels\n",
|
|
" expected_users = ['HILMI', 'VASYILLA', 'TANTI', 'YUDHA']\n",
|
|
" if y_pred_user[0] in expected_users:\n",
|
|
" update.message.reply_text(f\"Predicted User: {y_pred_user[0]} (Response Time: {user_prediction_time:.2f} ms)\")\n",
|
|
"\n",
|
|
" # Jika user dikenali, dilanjutkan dengan memproses suara ke fungsi speech to text dengan whisper\n",
|
|
" if 'pan menyala' in translation.lower():\n",
|
|
" send_command_to_firebase(\"Depan Menyala\")\n",
|
|
" update.message.reply_text(f\"Depan Menyala (Response Time: {translation_time:.2f} ms)\")\n",
|
|
" elif 'an manyala' in translation.lower():\n",
|
|
" send_command_to_firebase(\"Depan Menyala\")\n",
|
|
" update.message.reply_text(f\"Depan Menyala (Response Time: {translation_time:.2f} ms)\")\n",
|
|
" elif 'an mati' in translation.lower():\n",
|
|
" send_command_to_firebase(\"Depan Mati\")\n",
|
|
" update.message.reply_text(f\"Depan Mati (Response Time: {translation_time:.2f} ms)\")\n",
|
|
" elif 'samping menyala' in translation.lower():\n",
|
|
" send_command_to_firebase(\"Samping Menyala\")\n",
|
|
" update.message.reply_text(f\"Samping Menyala (Response Time: {translation_time:.2f} ms)\")\n",
|
|
" elif 'ing menyala' in translation.lower():\n",
|
|
" send_command_to_firebase(\"Samping Menyala\")\n",
|
|
" update.message.reply_text(f\"Samping Menyala (Response Time: {translation_time:.2f} ms)\")\n",
|
|
" elif 'samping mati' in translation.lower():\n",
|
|
" send_command_to_firebase(\"Samping Mati\")\n",
|
|
" update.message.reply_text(f\"Samping Mati (Response Time: {translation_time:.2f} ms)\")\n",
|
|
" elif 'ing mati' in translation.lower():\n",
|
|
" send_command_to_firebase(\"Samping Mati\")\n",
|
|
" update.message.reply_text(f\"Samping Mati (Response Time: {translation_time:.2f} ms)\")\n",
|
|
" elif 'tengah menyala' in translation.lower():\n",
|
|
" send_command_to_firebase(\"Tengah Menyala\")\n",
|
|
" update.message.reply_text(f\"Tengah Menyala (Response Time: {translation_time:.2f} ms)\")\n",
|
|
" elif 'ngah, menyala' in translation.lower():\n",
|
|
" send_command_to_firebase(\"Tengah Menyala\")\n",
|
|
" update.message.reply_text(f\"Tengah Menyala (Response Time: {translation_time:.2f} ms)\")\n",
|
|
" elif 'ah, manyalah' in translation.lower():\n",
|
|
" send_command_to_firebase(\"Tengah Menyala\")\n",
|
|
" elif 'tengah mati' in translation.lower():\n",
|
|
" send_command_to_firebase(\"Tengah Mati\")\n",
|
|
" update.message.reply_text(f\"Tengah Mati(Response Time: {translation_time:.2f} ms)\")\n",
|
|
" else:\n",
|
|
" update.message.reply_text(f\"Label tidak dikenali\")\n",
|
|
" else:\n",
|
|
" update.message.reply_text(\"User tidak dikenali\")\n",
|
|
"\n",
|
|
" # Hapus file audio yang sudah di-download\n",
|
|
" os.remove(file_path)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"colab": {
|
|
"background_save": true,
|
|
"base_uri": "https://localhost:8080/"
|
|
},
|
|
"id": "xrB_fZEWeVn3",
|
|
"outputId": "0ba85899-8921-497f-d550-dc2165a2c5d2"
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"/usr/local/lib/python3.10/dist-packages/sklearn/base.py:439: UserWarning: X does not have valid feature names, but SVC was fitted with feature names\n",
|
|
" warnings.warn(\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Firebase update successful for Depan Menyala\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"/usr/local/lib/python3.10/dist-packages/sklearn/base.py:439: UserWarning: X does not have valid feature names, but SVC was fitted with feature names\n",
|
|
" warnings.warn(\n",
|
|
"/usr/local/lib/python3.10/dist-packages/sklearn/base.py:439: UserWarning: X does not have valid feature names, but SVC was fitted with feature names\n",
|
|
" warnings.warn(\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Firebase update successful for Depan Mati\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"/usr/local/lib/python3.10/dist-packages/sklearn/base.py:439: UserWarning: X does not have valid feature names, but SVC was fitted with feature names\n",
|
|
" warnings.warn(\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Firebase update successful for Samping Menyala\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"/usr/local/lib/python3.10/dist-packages/sklearn/base.py:439: UserWarning: X does not have valid feature names, but SVC was fitted with feature names\n",
|
|
" warnings.warn(\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Firebase update successful for Samping Mati\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"/usr/local/lib/python3.10/dist-packages/sklearn/base.py:439: UserWarning: X does not have valid feature names, but SVC was fitted with feature names\n",
|
|
" warnings.warn(\n",
|
|
"/usr/local/lib/python3.10/dist-packages/sklearn/base.py:439: UserWarning: X does not have valid feature names, but SVC was fitted with feature names\n",
|
|
" warnings.warn(\n",
|
|
"/usr/local/lib/python3.10/dist-packages/sklearn/base.py:439: UserWarning: X does not have valid feature names, but SVC was fitted with feature names\n",
|
|
" warnings.warn(\n",
|
|
"/usr/local/lib/python3.10/dist-packages/sklearn/base.py:439: UserWarning: X does not have valid feature names, but SVC was fitted with feature names\n",
|
|
" warnings.warn(\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Firebase update successful for Tengah Menyala\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"/usr/local/lib/python3.10/dist-packages/sklearn/base.py:439: UserWarning: X does not have valid feature names, but SVC was fitted with feature names\n",
|
|
" warnings.warn(\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Firebase update successful for Tengah Mati\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"updater = Updater(\"6727323206:AAHLV35b-yi3bZUU3LPHYe0p2M_sZWWSUWw\", use_context=True)\n",
|
|
"dp = updater.dispatcher\n",
|
|
"\n",
|
|
"# Menambahkan handler untuk pesan suara\n",
|
|
"dp.add_handler(MessageHandler(Filters.voice, voice_message_handler))\n",
|
|
"\n",
|
|
"# Mulai bot\n",
|
|
"updater.start_polling()\n",
|
|
"updater.idle()"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"accelerator": "GPU",
|
|
"colab": {
|
|
"gpuType": "T4",
|
|
"provenance": []
|
|
},
|
|
"kernelspec": {
|
|
"display_name": "Python 3",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"name": "python"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 0
|
|
} |