{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.7.10","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":7634,"databundleVersionId":46676,"isSourceIdPinned":false,"sourceType":"competition"}],"dockerImageVersionId":30121,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n for filename in filenames:\n print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:26:55.658851Z","iopub.execute_input":"2025-09-26T01:26:55.659186Z","iopub.status.idle":"2025-09-26T01:26:55.745504Z","shell.execute_reply.started":"2025-09-26T01:26:55.659116Z","shell.execute_reply":"2025-09-26T01:26:55.744665Z"}},"outputs":[{"name":"stdout","text":"/kaggle/input/tensorflow-speech-recognition-challenge/link_to_gcp_credits_form.txt\n/kaggle/input/tensorflow-speech-recognition-challenge/test.7z\n/kaggle/input/tensorflow-speech-recognition-challenge/sample_submission.7z\n/kaggle/input/tensorflow-speech-recognition-challenge/train.7z\n","output_type":"stream"}],"execution_count":1},{"cell_type":"code","source":"!pip install pyunpack\n!pip install patool\n!pip install py7zr","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:27:00.498152Z","iopub.execute_input":"2025-09-26T01:27:00.498463Z","iopub.status.idle":"2025-09-26T01:28:10.617524Z","shell.execute_reply.started":"2025-09-26T01:27:00.498407Z","shell.execute_reply":"2025-09-26T01:28:10.616557Z"}},"outputs":[{"name":"stdout","text":"Collecting pyunpack\n Downloading pyunpack-0.3-py2.py3-none-any.whl (4.1 kB)\nCollecting entrypoint2\n Downloading entrypoint2-1.1-py2.py3-none-any.whl (9.9 kB)\nCollecting easyprocess\n Downloading EasyProcess-1.1-py3-none-any.whl (8.7 kB)\nInstalling collected packages: entrypoint2, easyprocess, pyunpack\nSuccessfully installed easyprocess-1.1 entrypoint2-1.1 pyunpack-0.3\n\u001b[33mWARNING: Running pip as root will break packages and permissions. You should install packages reliably by using venv: https://pip.pypa.io/warnings/venv\u001b[0m\nCollecting patool\n Downloading patool-1.12-py2.py3-none-any.whl (77 kB)\n\u001b[K |████████████████████████████████| 77 kB 4.8 MB/s eta 0:00:01\n\u001b[?25hInstalling collected packages: patool\nSuccessfully installed patool-1.12\n\u001b[33mWARNING: Running pip as root will break packages and permissions. You should install packages reliably by using venv: https://pip.pypa.io/warnings/venv\u001b[0m\nCollecting py7zr\n Downloading py7zr-0.21.1-py3-none-any.whl (67 kB)\n\u001b[K |████████████████████████████████| 67 kB 3.6 MB/s eta 0:00:01\n\u001b[?25hCollecting pybcj<1.1.0,>=1.0.0\n Downloading pybcj-1.0.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (50 kB)\n\u001b[K |████████████████████████████████| 50 kB 6.4 MB/s eta 0:00:01\n\u001b[?25hRequirement already satisfied: texttable in /opt/conda/lib/python3.7/site-packages (from py7zr) (1.6.3)\nCollecting py7zr\n Downloading py7zr-0.21.0-py3-none-any.whl (67 kB)\n\u001b[K |████████████████████████████████| 67 kB 4.0 MB/s eta 0:00:01\n\u001b[?25h Downloading py7zr-0.20.8-py3-none-any.whl (67 kB)\n\u001b[K |████████████████████████████████| 67 kB 4.1 MB/s eta 0:00:01\n\u001b[?25h Downloading py7zr-0.20.7-py3-none-any.whl (66 kB)\n\u001b[K |████████████████████████████████| 66 kB 3.8 MB/s eta 0:00:01\n\u001b[?25h Downloading py7zr-0.20.6-py3-none-any.whl (66 kB)\n\u001b[K |████████████████████████████████| 66 kB 4.9 MB/s eta 0:00:01\n\u001b[?25hCollecting pyzstd>=0.14.4\n Downloading pyzstd-0.17.0.tar.gz (1.2 MB)\n\u001b[K |████████████████████████████████| 1.2 MB 53.1 MB/s eta 0:00:01\n\u001b[?25h Installing build dependencies ... \u001b[?25ldone\n\u001b[?25h Getting requirements to build wheel ... \u001b[?25ldone\n\u001b[?25h Installing backend dependencies ... \u001b[?25ldone\n\u001b[?25h Preparing wheel metadata ... \u001b[?25ldone\n\u001b[?25hCollecting pyppmd<1.1.0,>=0.18.1\n Downloading pyppmd-1.0.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (138 kB)\n\u001b[K |████████████████████████████████| 138 kB 77.3 MB/s eta 0:00:01\n\u001b[?25hCollecting multivolumefile>=0.2.3\n Downloading multivolumefile-0.2.3-py3-none-any.whl (17 kB)\nRequirement already satisfied: importlib-metadata in /opt/conda/lib/python3.7/site-packages (from py7zr) (3.4.0)\nRequirement already satisfied: psutil in /opt/conda/lib/python3.7/site-packages (from py7zr) (5.8.0)\nCollecting brotli>=1.0.9\n Downloading Brotli-1.1.0-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.whl (2.8 MB)\n\u001b[K |████████████████████████████████| 2.8 MB 61.5 MB/s eta 0:00:01\n\u001b[?25hCollecting inflate64>=0.3.1\n Downloading inflate64-0.3.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (93 kB)\n\u001b[K |████████████████████████████████| 93 kB 1.8 MB/s eta 0:00:01\n\u001b[?25hCollecting pycryptodomex>=3.6.6\n Downloading pycryptodomex-3.23.0-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.3 MB)\n\u001b[K |████████████████████████████████| 2.3 MB 70.7 MB/s eta 0:00:01\n\u001b[?25hCollecting pyzstd>=0.14.4\n Downloading pyzstd-0.16.2.tar.gz (789 kB)\n\u001b[K |████████████████████████████████| 789 kB 31.4 MB/s eta 0:00:01\n\u001b[?25h Installing build dependencies ... \u001b[?25ldone\n\u001b[?25h Getting requirements to build wheel ... \u001b[?25ldone\n\u001b[?25h Installing backend dependencies ... \u001b[?25ldone\n\u001b[?25h Preparing wheel metadata ... \u001b[?25ldone\n\u001b[?25hRequirement already satisfied: zipp>=0.5 in /opt/conda/lib/python3.7/site-packages (from importlib-metadata->py7zr) (3.4.1)\nRequirement already satisfied: typing-extensions>=3.6.4 in /opt/conda/lib/python3.7/site-packages (from importlib-metadata->py7zr) (3.7.4.3)\nBuilding wheels for collected packages: pyzstd\n Building wheel for pyzstd (PEP 517) ... \u001b[?25ldone\n\u001b[?25h Created wheel for pyzstd: filename=pyzstd-0.16.2-cp37-cp37m-linux_x86_64.whl size=410863 sha256=aa3b935b4089326a18b4322f1b2eec1da8cc4d8956b322a55dd15e98b451bae4\n Stored in directory: /root/.cache/pip/wheels/67/6a/4b/879230212b88a579adf46bbc2f07619669c6bf94c786e3fac3\nSuccessfully built pyzstd\nInstalling collected packages: pyzstd, pyppmd, pycryptodomex, pybcj, multivolumefile, inflate64, brotli, py7zr\nSuccessfully installed brotli-1.1.0 inflate64-0.3.1 multivolumefile-0.2.3 py7zr-0.20.6 pybcj-1.0.1 pycryptodomex-3.23.0 pyppmd-1.0.0 pyzstd-0.16.2\n\u001b[33mWARNING: Running pip as root will break packages and permissions. You should install packages reliably by using venv: https://pip.pypa.io/warnings/venv\u001b[0m\n","output_type":"stream"}],"execution_count":2},{"cell_type":"code","source":"from py7zr import unpack_7zarchive\nimport shutil\n\nshutil.register_unpack_format('7zip', ['.7z'], unpack_7zarchive)\nshutil.unpack_archive('/kaggle/input/tensorflow-speech-recognition-challenge/train.7z', '/kaggle/working/tensorflow-speech-recognition-challenge/train/')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:28:40.053676Z","iopub.execute_input":"2025-09-26T01:28:40.053991Z","iopub.status.idle":"2025-09-26T01:37:32.40441Z","shell.execute_reply.started":"2025-09-26T01:28:40.053948Z","shell.execute_reply":"2025-09-26T01:37:32.403649Z"}},"outputs":[],"execution_count":3},{"cell_type":"code","source":"# from pyunpack import Archive\n# import shutil\n# if not os.path.exists('/kaggle/working/tensorflow-speech-recognition-challenge/train/'):\n# os.makedirs('/kaggle/working/tensorflow-speech-recognition-challenge/train/')\n# Archive('/kaggle/input/tensorflow-speech-recognition-challenge/train.7z').extractall('/kaggle/working/tensorflow-speech-recognition-challenge/train/')\n\nfor dirname, _, filenames in os.walk('/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio'):\n for filename in filename[:5]:\n print(os.path.join(dirname, filename))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:39:23.633341Z","iopub.execute_input":"2025-09-26T01:39:23.63367Z","iopub.status.idle":"2025-09-26T01:39:23.731046Z","shell.execute_reply.started":"2025-09-26T01:39:23.633643Z","shell.execute_reply":"2025-09-26T01:39:23.730151Z"}},"outputs":[{"name":"stdout","text":"/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/t\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/r\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/a\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/i\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/nine/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/zero/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/cat/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/five/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/tree/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/eight/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/happy/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/go/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/wow/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/stop/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/bird/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/_background_noise_/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/down/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/seven/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/dog/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/six/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/sheila/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/house/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/left/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/bed/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/one/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/four/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/no/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/up/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/off/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/yes/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/two/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/on/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/marvin/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/three/n\n/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/right/n\n","output_type":"stream"}],"execution_count":4},{"cell_type":"code","source":"import warnings\nwarnings.filterwarnings(\"ignore\")\n\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nimport librosa\nimport IPython.display as ipd\nfrom scipy.io import wavfile","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:39:37.653661Z","iopub.execute_input":"2025-09-26T01:39:37.65396Z","iopub.status.idle":"2025-09-26T01:39:39.713719Z","shell.execute_reply.started":"2025-09-26T01:39:37.653935Z","shell.execute_reply":"2025-09-26T01:39:39.712866Z"}},"outputs":[],"execution_count":5},{"cell_type":"code","source":"train_audio_path = '/kaggle/working/tensorflow-speech-recognition-challenge/train/train/audio/'","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:39:45.664595Z","iopub.execute_input":"2025-09-26T01:39:45.664906Z","iopub.status.idle":"2025-09-26T01:39:45.668824Z","shell.execute_reply.started":"2025-09-26T01:39:45.664878Z","shell.execute_reply":"2025-09-26T01:39:45.667945Z"}},"outputs":[],"execution_count":6},{"cell_type":"code","source":"samples, sample_rate = librosa.load(train_audio_path+'yes/0a7c2a8d_nohash_0.wav', sr = 16000)\nfig = plt.figure(figsize=(14, 8))\nax1 = fig.add_subplot(211)\nax1.set_title('Raw wave of ' + '../input/train/audio/yes/0a7c2a8d_nohash_0.wav')\nax1.set_xlabel('time')\nax1.set_ylabel('Amplitude')\nax1.plot(np.linspace(0, sample_rate/len(samples), sample_rate), samples)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:39:48.133244Z","iopub.execute_input":"2025-09-26T01:39:48.133592Z","iopub.status.idle":"2025-09-26T01:39:48.339091Z","shell.execute_reply.started":"2025-09-26T01:39:48.133561Z","shell.execute_reply":"2025-09-26T01:39:48.338328Z"}},"outputs":[{"execution_count":7,"output_type":"execute_result","data":{"text/plain":"[]"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{"needs_background":"light"}}],"execution_count":7},{"cell_type":"code","source":"samples, sample_rate = librosa.load(train_audio_path+'yes/0a7c2a8d_nohash_0.wav', sr = 100)\nfig = plt.figure(figsize=(14, 8))\nax1 = fig.add_subplot(211)\nax1.set_title('Raw wave of ' + '../input/train/audio/yes/0a7c2a8d_nohash_0.wav')\nax1.set_xlabel('time')\nax1.set_ylabel('Amplitude')\nax1.plot(np.linspace(0, sample_rate/len(samples), sample_rate), samples)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:39:51.068074Z","iopub.execute_input":"2025-09-26T01:39:51.068359Z","iopub.status.idle":"2025-09-26T01:39:51.876744Z","shell.execute_reply.started":"2025-09-26T01:39:51.068334Z","shell.execute_reply":"2025-09-26T01:39:51.875916Z"}},"outputs":[{"execution_count":8,"output_type":"execute_result","data":{"text/plain":"[]"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{"needs_background":"light"}}],"execution_count":8},{"cell_type":"code","source":"sample_rate=40000\nsamples, sample_rate = librosa.load(train_audio_path+'yes/0a7c2a8d_nohash_0.wav', sr = sample_rate)\nipd.Audio(samples, rate=sample_rate)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:39:56.593249Z","iopub.execute_input":"2025-09-26T01:39:56.593625Z","iopub.status.idle":"2025-09-26T01:39:56.646355Z","shell.execute_reply.started":"2025-09-26T01:39:56.593597Z","shell.execute_reply":"2025-09-26T01:39:56.645522Z"}},"outputs":[{"execution_count":9,"output_type":"execute_result","data":{"text/plain":"","text/html":"\n \n "},"metadata":{}}],"execution_count":9},{"cell_type":"code","source":"sample_rate=16000\nsamples, sample_rate = librosa.load(train_audio_path+'yes/0a7c2a8d_nohash_0.wav', sr = sample_rate)\nipd.Audio(samples, rate=sample_rate)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:40:22.493159Z","iopub.execute_input":"2025-09-26T01:40:22.493549Z","iopub.status.idle":"2025-09-26T01:40:22.501109Z","shell.execute_reply.started":"2025-09-26T01:40:22.493515Z","shell.execute_reply":"2025-09-26T01:40:22.500323Z"}},"outputs":[{"execution_count":10,"output_type":"execute_result","data":{"text/plain":"","text/html":"\n \n "},"metadata":{}}],"execution_count":10},{"cell_type":"code","source":"sample_rate=6000\nsamples, sample_rate = librosa.load(train_audio_path+'yes/0a7c2a8d_nohash_0.wav', sr = sample_rate)\nipd.Audio(samples, rate=sample_rate)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:40:27.203222Z","iopub.execute_input":"2025-09-26T01:40:27.20356Z","iopub.status.idle":"2025-09-26T01:40:27.226923Z","shell.execute_reply.started":"2025-09-26T01:40:27.203527Z","shell.execute_reply":"2025-09-26T01:40:27.226085Z"}},"outputs":[{"execution_count":11,"output_type":"execute_result","data":{"text/plain":"","text/html":"\n \n "},"metadata":{}}],"execution_count":11},{"cell_type":"code","source":"sample_rate=3000\nsamples, sample_rate = librosa.load(train_audio_path+'yes/0a7c2a8d_nohash_0.wav', sr = sample_rate)\nipd.Audio(samples, rate=sample_rate)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:40:29.853008Z","iopub.execute_input":"2025-09-26T01:40:29.853337Z","iopub.status.idle":"2025-09-26T01:40:29.876219Z","shell.execute_reply.started":"2025-09-26T01:40:29.853307Z","shell.execute_reply":"2025-09-26T01:40:29.875341Z"}},"outputs":[{"execution_count":12,"output_type":"execute_result","data":{"text/plain":"","text/html":"\n \n "},"metadata":{}}],"execution_count":12},{"cell_type":"code","source":"samples = librosa.resample(samples, sample_rate, 8000)\nipd.Audio(samples, rate=8000)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:40:35.668752Z","iopub.execute_input":"2025-09-26T01:40:35.669059Z","iopub.status.idle":"2025-09-26T01:40:35.685918Z","shell.execute_reply.started":"2025-09-26T01:40:35.669031Z","shell.execute_reply":"2025-09-26T01:40:35.684934Z"}},"outputs":[{"execution_count":13,"output_type":"execute_result","data":{"text/plain":"","text/html":"\n \n "},"metadata":{}}],"execution_count":13},{"cell_type":"code","source":"labels=os.listdir(train_audio_path)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:40:40.913064Z","iopub.execute_input":"2025-09-26T01:40:40.913383Z","iopub.status.idle":"2025-09-26T01:40:40.917462Z","shell.execute_reply.started":"2025-09-26T01:40:40.913352Z","shell.execute_reply":"2025-09-26T01:40:40.916527Z"}},"outputs":[],"execution_count":14},{"cell_type":"code","source":"#find count of each label and plot bar graph\nno_of_recordings=[]\nfor label in labels:\n waves = [f for f in os.listdir(train_audio_path + '/'+ label) if f.endswith('.wav')]\n no_of_recordings.append(len(waves))\n \n#plot\nplt.figure(figsize=(30,5))\nindex = np.arange(len(labels))\nplt.bar(index, no_of_recordings)\nplt.xlabel('Commands', fontsize=12)\nplt.ylabel('No of recordings', fontsize=12)\nplt.xticks(index, labels, fontsize=15, rotation=60)\nplt.title('No. of recordings for each command')\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:40:46.053248Z","iopub.execute_input":"2025-09-26T01:40:46.0536Z","iopub.status.idle":"2025-09-26T01:40:46.389219Z","shell.execute_reply.started":"2025-09-26T01:40:46.053567Z","shell.execute_reply":"2025-09-26T01:40:46.38848Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{"needs_background":"light"}}],"execution_count":15},{"cell_type":"code","source":"# labels=[\"yes\", \"no\",\"stop\", \"go\"]\nlabels=[\"yes\", \"no\", \"up\", \"down\", \"left\", \"right\", \"on\", \"off\", \"stop\", \"go\"]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:40:48.538253Z","iopub.execute_input":"2025-09-26T01:40:48.538553Z","iopub.status.idle":"2025-09-26T01:40:48.542661Z","shell.execute_reply.started":"2025-09-26T01:40:48.538528Z","shell.execute_reply":"2025-09-26T01:40:48.54168Z"}},"outputs":[],"execution_count":16},{"cell_type":"code","source":"duration_of_recordings=[]\nfor label in labels:\n waves = [f for f in os.listdir(train_audio_path + '/'+ label) if f.endswith('.wav')]\n for wav in waves:\n sample_rate, samples = wavfile.read(train_audio_path + '/' + label + '/' + wav)\n duration_of_recordings.append(float(len(samples)/sample_rate))\n \nplt.hist(np.array(duration_of_recordings))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:40:51.113072Z","iopub.execute_input":"2025-09-26T01:40:51.113438Z","iopub.status.idle":"2025-09-26T01:40:52.678313Z","shell.execute_reply.started":"2025-09-26T01:40:51.113387Z","shell.execute_reply":"2025-09-26T01:40:52.677506Z"}},"outputs":[{"execution_count":17,"output_type":"execute_result","data":{"text/plain":"(array([1.5000e+01, 3.0000e+01, 4.4000e+01, 1.3800e+02, 1.3600e+02,\n 1.7900e+02, 3.6600e+02, 4.3400e+02, 5.9300e+02, 2.1747e+04]),\n array([0.418 , 0.4762, 0.5344, 0.5926, 0.6508, 0.709 , 0.7672, 0.8254,\n 0.8836, 0.9418, 1. ]),\n )"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{"needs_background":"light"}}],"execution_count":17},{"cell_type":"code","source":"all_wave = []\nall_label = []\nfor label in labels:\n print(label)\n waves = [f for f in os.listdir(train_audio_path + '/'+ label) if f.endswith('.wav')]\n for wav in waves:\n samples, sample_rate = librosa.load(train_audio_path + '/' + label + '/' + wav, sr = 16000)\n samples = librosa.resample(samples, sample_rate, 8000)\n if(len(samples)== 8000) : \n all_wave.append(samples)\n all_label.append(label)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:44:56.673159Z","iopub.execute_input":"2025-09-26T01:44:56.673483Z","iopub.status.idle":"2025-09-26T01:50:56.8776Z","shell.execute_reply.started":"2025-09-26T01:44:56.673445Z","shell.execute_reply":"2025-09-26T01:50:56.876876Z"}},"outputs":[{"name":"stdout","text":"yes\nno\nup\ndown\nleft\nright\non\noff\nstop\ngo\n","output_type":"stream"}],"execution_count":19},{"cell_type":"code","source":"print(type(all_wave))\nprint(len(all_wave))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:56:15.768594Z","iopub.execute_input":"2025-09-26T01:56:15.768919Z","iopub.status.idle":"2025-09-26T01:56:15.773668Z","shell.execute_reply.started":"2025-09-26T01:56:15.768892Z","shell.execute_reply":"2025-09-26T01:56:15.772783Z"}},"outputs":[{"name":"stdout","text":"\n21312\n","output_type":"stream"}],"execution_count":20},{"cell_type":"code","source":"print(len(all_wave))\nprint(all_wave[1].shape)\nall_wave[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:56:19.617945Z","iopub.execute_input":"2025-09-26T01:56:19.618239Z","iopub.status.idle":"2025-09-26T01:56:19.625363Z","shell.execute_reply.started":"2025-09-26T01:56:19.618213Z","shell.execute_reply":"2025-09-26T01:56:19.624511Z"}},"outputs":[{"name":"stdout","text":"21312\n(8000,)\n","output_type":"stream"},{"execution_count":21,"output_type":"execute_result","data":{"text/plain":"array([ 0.00076987, 0.00291408, 0.00481603, ..., -0.00424195,\n -0.00535484, -0.00386438], dtype=float32)"},"metadata":{}}],"execution_count":21},{"cell_type":"code","source":"len(set(all_label))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:56:22.587922Z","iopub.execute_input":"2025-09-26T01:56:22.588249Z","iopub.status.idle":"2025-09-26T01:56:22.593741Z","shell.execute_reply.started":"2025-09-26T01:56:22.588217Z","shell.execute_reply":"2025-09-26T01:56:22.592842Z"}},"outputs":[{"execution_count":22,"output_type":"execute_result","data":{"text/plain":"10"},"metadata":{}}],"execution_count":22},{"cell_type":"code","source":"from sklearn.preprocessing import LabelEncoder\nle = LabelEncoder()\ny=le.fit_transform(all_label)\nclasses= list(le.classes_)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:56:23.608151Z","iopub.execute_input":"2025-09-26T01:56:23.608479Z","iopub.status.idle":"2025-09-26T01:56:23.618077Z","shell.execute_reply.started":"2025-09-26T01:56:23.60845Z","shell.execute_reply":"2025-09-26T01:56:23.617362Z"}},"outputs":[],"execution_count":23},{"cell_type":"code","source":"classes","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:56:25.078016Z","iopub.execute_input":"2025-09-26T01:56:25.078305Z","iopub.status.idle":"2025-09-26T01:56:25.083844Z","shell.execute_reply.started":"2025-09-26T01:56:25.078279Z","shell.execute_reply":"2025-09-26T01:56:25.082968Z"}},"outputs":[{"execution_count":24,"output_type":"execute_result","data":{"text/plain":"['down', 'go', 'left', 'no', 'off', 'on', 'right', 'stop', 'up', 'yes']"},"metadata":{}}],"execution_count":24},{"cell_type":"code","source":"from keras.utils import np_utils\ny=np_utils.to_categorical(y, num_classes=len(labels))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:56:29.517984Z","iopub.execute_input":"2025-09-26T01:56:29.518287Z","iopub.status.idle":"2025-09-26T01:56:34.489399Z","shell.execute_reply.started":"2025-09-26T01:56:29.518261Z","shell.execute_reply":"2025-09-26T01:56:34.488538Z"}},"outputs":[],"execution_count":25},{"cell_type":"code","source":"y","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:56:40.673208Z","iopub.execute_input":"2025-09-26T01:56:40.673519Z","iopub.status.idle":"2025-09-26T01:56:40.67961Z","shell.execute_reply.started":"2025-09-26T01:56:40.673489Z","shell.execute_reply":"2025-09-26T01:56:40.678801Z"}},"outputs":[{"execution_count":26,"output_type":"execute_result","data":{"text/plain":"array([[0., 0., 0., ..., 0., 0., 1.],\n [0., 0., 0., ..., 0., 0., 1.],\n [0., 0., 0., ..., 0., 0., 1.],\n ...,\n [0., 1., 0., ..., 0., 0., 0.],\n [0., 1., 0., ..., 0., 0., 0.],\n [0., 1., 0., ..., 0., 0., 0.]], dtype=float32)"},"metadata":{}}],"execution_count":26},{"cell_type":"markdown","source":"Reshape the 2D array to 3D since the input to the conv1d must be a 3D array:","metadata":{}},{"cell_type":"code","source":"all_wave = np.array(all_wave).reshape(-1,8000,1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:56:43.654332Z","iopub.execute_input":"2025-09-26T01:56:43.65465Z","iopub.status.idle":"2025-09-26T01:56:43.885905Z","shell.execute_reply.started":"2025-09-26T01:56:43.654623Z","shell.execute_reply":"2025-09-26T01:56:43.885092Z"}},"outputs":[],"execution_count":27},{"cell_type":"code","source":"all_wave.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:56:45.053265Z","iopub.execute_input":"2025-09-26T01:56:45.053627Z","iopub.status.idle":"2025-09-26T01:56:45.05886Z","shell.execute_reply.started":"2025-09-26T01:56:45.053599Z","shell.execute_reply":"2025-09-26T01:56:45.05796Z"}},"outputs":[{"execution_count":28,"output_type":"execute_result","data":{"text/plain":"(21312, 8000, 1)"},"metadata":{}}],"execution_count":28},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nx_tr, x_val, y_tr, y_val = train_test_split(np.array(all_wave),np.array(y),stratify=y,test_size = 0.2,random_state=777,shuffle=True)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:56:47.74325Z","iopub.execute_input":"2025-09-26T01:56:47.743655Z","iopub.status.idle":"2025-09-26T01:56:48.374208Z","shell.execute_reply.started":"2025-09-26T01:56:47.743624Z","shell.execute_reply":"2025-09-26T01:56:48.373343Z"}},"outputs":[],"execution_count":29},{"cell_type":"markdown","source":"","metadata":{}},{"cell_type":"code","source":"from keras.layers import Dense, Dropout, Flatten, Conv1D, Input, MaxPooling1D\nfrom keras.models import Model\nfrom keras.callbacks import EarlyStopping, ModelCheckpoint\nfrom keras import backend as K\nK.clear_session()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:56:54.761757Z","iopub.execute_input":"2025-09-26T01:56:54.762069Z","iopub.status.idle":"2025-09-26T01:56:54.777466Z","shell.execute_reply.started":"2025-09-26T01:56:54.762039Z","shell.execute_reply":"2025-09-26T01:56:54.776678Z"}},"outputs":[],"execution_count":30},{"cell_type":"code","source":"# ?Conv1D","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:56:56.063597Z","iopub.execute_input":"2025-09-26T01:56:56.063886Z","iopub.status.idle":"2025-09-26T01:56:56.067214Z","shell.execute_reply.started":"2025-09-26T01:56:56.06386Z","shell.execute_reply":"2025-09-26T01:56:56.066337Z"}},"outputs":[],"execution_count":31},{"cell_type":"code","source":"inputs = Input(shape=(8000,1))\n\n#First Conv1D layer\nconv = Conv1D(filters=8,kernel_size=13, padding='valid', activation='relu', strides=1)(inputs)\nconv = MaxPooling1D(3)(conv)\nconv = Dropout(0.3)(conv)\n\n#Second Conv1D layer\nconv = Conv1D(16, 11, padding='valid', activation='relu', strides=1)(conv)\nconv = MaxPooling1D(3)(conv)\nconv = Dropout(0.3)(conv)\n\n#Third Conv1D layer\nconv = Conv1D(32, 9, padding='valid', activation='relu', strides=1)(conv)\nconv = MaxPooling1D(3)(conv)\nconv = Dropout(0.3)(conv)\n\n#Fourth Conv1D layer\nconv = Conv1D(64, 7, padding='valid', activation='relu', strides=1)(conv)\nconv = MaxPooling1D(3)(conv)\nconv = Dropout(0.3)(conv)\n\n#Flatten layer\nconv = Flatten()(conv)\n\n#Dense Layer 1\nconv = Dense(256, activation='relu')(conv)\nconv = Dropout(0.3)(conv)\n\n#Dense Layer 2\nconv = Dense(128, activation='relu')(conv)\nconv = Dropout(0.3)(conv)\n\noutputs = Dense(len(labels), activation='softmax')(conv)\n\nmodel = Model(inputs, outputs)\nmodel.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:56:57.263074Z","iopub.execute_input":"2025-09-26T01:56:57.263363Z","iopub.status.idle":"2025-09-26T01:56:59.246187Z","shell.execute_reply.started":"2025-09-26T01:56:57.263338Z","shell.execute_reply":"2025-09-26T01:56:59.245449Z"}},"outputs":[{"name":"stdout","text":"Model: \"model\"\n_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\ninput_1 (InputLayer) [(None, 8000, 1)] 0 \n_________________________________________________________________\nconv1d (Conv1D) (None, 7988, 8) 112 \n_________________________________________________________________\nmax_pooling1d (MaxPooling1D) (None, 2662, 8) 0 \n_________________________________________________________________\ndropout (Dropout) (None, 2662, 8) 0 \n_________________________________________________________________\nconv1d_1 (Conv1D) (None, 2652, 16) 1424 \n_________________________________________________________________\nmax_pooling1d_1 (MaxPooling1 (None, 884, 16) 0 \n_________________________________________________________________\ndropout_1 (Dropout) (None, 884, 16) 0 \n_________________________________________________________________\nconv1d_2 (Conv1D) (None, 876, 32) 4640 \n_________________________________________________________________\nmax_pooling1d_2 (MaxPooling1 (None, 292, 32) 0 \n_________________________________________________________________\ndropout_2 (Dropout) (None, 292, 32) 0 \n_________________________________________________________________\nconv1d_3 (Conv1D) (None, 286, 64) 14400 \n_________________________________________________________________\nmax_pooling1d_3 (MaxPooling1 (None, 95, 64) 0 \n_________________________________________________________________\ndropout_3 (Dropout) (None, 95, 64) 0 \n_________________________________________________________________\nflatten (Flatten) (None, 6080) 0 \n_________________________________________________________________\ndense (Dense) (None, 256) 1556736 \n_________________________________________________________________\ndropout_4 (Dropout) (None, 256) 0 \n_________________________________________________________________\ndense_1 (Dense) (None, 128) 32896 \n_________________________________________________________________\ndropout_5 (Dropout) (None, 128) 0 \n_________________________________________________________________\ndense_2 (Dense) (None, 10) 1290 \n=================================================================\nTotal params: 1,611,498\nTrainable params: 1,611,498\nNon-trainable params: 0\n_________________________________________________________________\n","output_type":"stream"}],"execution_count":32},{"cell_type":"code","source":"model.compile(loss='categorical_crossentropy',optimizer='adam',metrics=['accuracy'])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:57:03.533043Z","iopub.execute_input":"2025-09-26T01:57:03.533339Z","iopub.status.idle":"2025-09-26T01:57:03.547462Z","shell.execute_reply.started":"2025-09-26T01:57:03.533315Z","shell.execute_reply":"2025-09-26T01:57:03.546761Z"}},"outputs":[],"execution_count":33},{"cell_type":"code","source":"es = EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=10, min_delta=0.0001) \nmc = ModelCheckpoint('best_model.hdf5', monitor='val_acc', verbose=1, save_best_only=True, mode='max')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:57:06.603122Z","iopub.execute_input":"2025-09-26T01:57:06.603506Z","iopub.status.idle":"2025-09-26T01:57:06.607818Z","shell.execute_reply.started":"2025-09-26T01:57:06.603473Z","shell.execute_reply":"2025-09-26T01:57:06.606856Z"}},"outputs":[],"execution_count":34},{"cell_type":"code","source":"history=model.fit(x_tr, y_tr ,epochs=100, callbacks=[es,mc], batch_size=32, validation_data=(x_val,y_val))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T01:57:09.933073Z","iopub.execute_input":"2025-09-26T01:57:09.933399Z","iopub.status.idle":"2025-09-26T02:00:08.858794Z","shell.execute_reply.started":"2025-09-26T01:57:09.933368Z","shell.execute_reply":"2025-09-26T02:00:08.857838Z"}},"outputs":[{"name":"stdout","text":"Epoch 1/100\n533/533 [==============================] - 12s 8ms/step - loss: 2.2059 - accuracy: 0.1575 - val_loss: 1.6850 - val_accuracy: 0.3662\nEpoch 2/100\n533/533 [==============================] - 4s 7ms/step - loss: 1.5775 - accuracy: 0.4035 - val_loss: 1.2887 - val_accuracy: 0.5435\nEpoch 3/100\n533/533 [==============================] - 4s 7ms/step - loss: 1.2959 - accuracy: 0.5252 - val_loss: 1.1191 - val_accuracy: 0.6151\nEpoch 4/100\n533/533 [==============================] - 4s 7ms/step - loss: 1.1624 - accuracy: 0.5790 - val_loss: 1.0020 - val_accuracy: 0.6620\nEpoch 5/100\n533/533 [==============================] - 4s 7ms/step - loss: 1.0320 - accuracy: 0.6400 - val_loss: 0.9040 - val_accuracy: 0.6918\nEpoch 6/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.9364 - accuracy: 0.6707 - val_loss: 0.8676 - val_accuracy: 0.7187\nEpoch 7/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.8438 - accuracy: 0.7098 - val_loss: 0.7787 - val_accuracy: 0.7274\nEpoch 8/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.7636 - accuracy: 0.7307 - val_loss: 0.6999 - val_accuracy: 0.7617\nEpoch 9/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.7204 - accuracy: 0.7510 - val_loss: 0.6246 - val_accuracy: 0.7868\nEpoch 10/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.6558 - accuracy: 0.7734 - val_loss: 0.6535 - val_accuracy: 0.7847\nEpoch 11/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.6054 - accuracy: 0.7920 - val_loss: 0.6231 - val_accuracy: 0.7882\nEpoch 12/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.5818 - accuracy: 0.7931 - val_loss: 0.5893 - val_accuracy: 0.8013\nEpoch 13/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.5562 - accuracy: 0.8078 - val_loss: 0.6077 - val_accuracy: 0.7999\nEpoch 14/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.5391 - accuracy: 0.8183 - val_loss: 0.5690 - val_accuracy: 0.8037\nEpoch 15/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.5216 - accuracy: 0.8210 - val_loss: 0.5731 - val_accuracy: 0.8065\nEpoch 16/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.4785 - accuracy: 0.8380 - val_loss: 0.5271 - val_accuracy: 0.8262\nEpoch 17/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.4725 - accuracy: 0.8370 - val_loss: 0.5122 - val_accuracy: 0.8337\nEpoch 18/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.4337 - accuracy: 0.8504 - val_loss: 0.5096 - val_accuracy: 0.8292\nEpoch 19/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.4369 - accuracy: 0.8474 - val_loss: 0.5177 - val_accuracy: 0.8283\nEpoch 20/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.4218 - accuracy: 0.8541 - val_loss: 0.5261 - val_accuracy: 0.8252\nEpoch 21/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.4100 - accuracy: 0.8571 - val_loss: 0.5037 - val_accuracy: 0.8337\nEpoch 22/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.3999 - accuracy: 0.8644 - val_loss: 0.5089 - val_accuracy: 0.8353\nEpoch 23/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.3746 - accuracy: 0.8735 - val_loss: 0.5312 - val_accuracy: 0.8248\nEpoch 24/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.3711 - accuracy: 0.8728 - val_loss: 0.5273 - val_accuracy: 0.8191\nEpoch 25/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.3608 - accuracy: 0.8706 - val_loss: 0.5270 - val_accuracy: 0.8264\nEpoch 26/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.3560 - accuracy: 0.8729 - val_loss: 0.5067 - val_accuracy: 0.8370\nEpoch 27/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.3562 - accuracy: 0.8802 - val_loss: 0.5375 - val_accuracy: 0.8299\nEpoch 28/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.3378 - accuracy: 0.8805 - val_loss: 0.5129 - val_accuracy: 0.8365\nEpoch 29/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.3267 - accuracy: 0.8856 - val_loss: 0.5574 - val_accuracy: 0.8163\nEpoch 30/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.3207 - accuracy: 0.8877 - val_loss: 0.4872 - val_accuracy: 0.8456\nEpoch 31/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.2981 - accuracy: 0.8964 - val_loss: 0.5075 - val_accuracy: 0.8417\nEpoch 32/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.3107 - accuracy: 0.8946 - val_loss: 0.5014 - val_accuracy: 0.8386\nEpoch 33/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.3125 - accuracy: 0.8940 - val_loss: 0.5058 - val_accuracy: 0.8379\nEpoch 34/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.2988 - accuracy: 0.8961 - val_loss: 0.5011 - val_accuracy: 0.8431\nEpoch 35/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.2982 - accuracy: 0.9022 - val_loss: 0.4793 - val_accuracy: 0.8496\nEpoch 36/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.2936 - accuracy: 0.8993 - val_loss: 0.4695 - val_accuracy: 0.8487\nEpoch 37/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.2874 - accuracy: 0.9028 - val_loss: 0.5117 - val_accuracy: 0.8442\nEpoch 38/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.2750 - accuracy: 0.9066 - val_loss: 0.4892 - val_accuracy: 0.8449\nEpoch 39/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.2783 - accuracy: 0.9026 - val_loss: 0.5011 - val_accuracy: 0.8452\nEpoch 40/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.2754 - accuracy: 0.9102 - val_loss: 0.4949 - val_accuracy: 0.8412\nEpoch 41/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.2523 - accuracy: 0.9141 - val_loss: 0.4816 - val_accuracy: 0.8468\nEpoch 42/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.2775 - accuracy: 0.9027 - val_loss: 0.4972 - val_accuracy: 0.8456\nEpoch 43/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.2729 - accuracy: 0.9092 - val_loss: 0.5222 - val_accuracy: 0.8365\nEpoch 44/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.2557 - accuracy: 0.9115 - val_loss: 0.5160 - val_accuracy: 0.8431\nEpoch 45/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.2498 - accuracy: 0.9162 - val_loss: 0.5183 - val_accuracy: 0.8447\nEpoch 46/100\n533/533 [==============================] - 4s 7ms/step - loss: 0.2502 - accuracy: 0.9157 - val_loss: 0.4979 - val_accuracy: 0.8468\nEpoch 00046: early stopping\n","output_type":"stream"}],"execution_count":35},{"cell_type":"code","source":"from matplotlib import pyplot\npyplot.plot(history.history['loss'], label='train')\npyplot.plot(history.history['val_loss'], label='test')\npyplot.legend()\npyplot.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T02:02:56.064061Z","iopub.execute_input":"2025-09-26T02:02:56.06448Z","iopub.status.idle":"2025-09-26T02:02:56.199378Z","shell.execute_reply.started":"2025-09-26T02:02:56.06444Z","shell.execute_reply":"2025-09-26T02:02:56.198498Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{"needs_background":"light"}}],"execution_count":36},{"cell_type":"code","source":"from keras.models import load_model\nmodel.save(\"SpeechRecogModel.h5\")\n#model=load_model('/kaggle/working/best_model.hdf5')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T02:03:00.213012Z","iopub.execute_input":"2025-09-26T02:03:00.213347Z","iopub.status.idle":"2025-09-26T02:03:00.29137Z","shell.execute_reply.started":"2025-09-26T02:03:00.213315Z","shell.execute_reply":"2025-09-26T02:03:00.290602Z"}},"outputs":[],"execution_count":37},{"cell_type":"code","source":"def predict(audio):\n prob=model.predict(audio.reshape(1,8000,1))\n index=np.argmax(prob[0])\n return classes[index]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T02:03:03.532891Z","iopub.execute_input":"2025-09-26T02:03:03.533181Z","iopub.status.idle":"2025-09-26T02:03:03.53748Z","shell.execute_reply.started":"2025-09-26T02:03:03.533154Z","shell.execute_reply":"2025-09-26T02:03:03.536506Z"}},"outputs":[],"execution_count":38},{"cell_type":"code","source":"import random\nindex=random.randint(0,len(x_val)-1)\nsamples=x_val[index].ravel()\nprint(\"Audio:\",classes[np.argmax(y_val[index])])\nipd.Audio(samples, rate=8000)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T02:22:48.058226Z","iopub.execute_input":"2025-09-26T02:22:48.058563Z","iopub.status.idle":"2025-09-26T02:22:48.066808Z","shell.execute_reply.started":"2025-09-26T02:22:48.058531Z","shell.execute_reply":"2025-09-26T02:22:48.065954Z"}},"outputs":[{"name":"stdout","text":"Audio: yes\n","output_type":"stream"},{"execution_count":65,"output_type":"execute_result","data":{"text/plain":"","text/html":"\n \n "},"metadata":{}}],"execution_count":65},{"cell_type":"code","source":"print(\"Text:\",predict(samples))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T02:22:57.582951Z","iopub.execute_input":"2025-09-26T02:22:57.583238Z","iopub.status.idle":"2025-09-26T02:22:57.623143Z","shell.execute_reply.started":"2025-09-26T02:22:57.583211Z","shell.execute_reply":"2025-09-26T02:22:57.622251Z"}},"outputs":[{"name":"stdout","text":"Text: yes\n","output_type":"stream"}],"execution_count":66},{"cell_type":"code","source":"import IPython.display as ipd\n\nipd.Audio(\"/kaggle/input/audio-file/Conference.wav\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-26T02:15:23.433356Z","iopub.execute_input":"2025-09-26T02:15:23.433726Z","iopub.status.idle":"2025-09-26T02:15:23.456237Z","shell.execute_reply.started":"2025-09-26T02:15:23.433695Z","shell.execute_reply":"2025-09-26T02:15:23.455372Z"}},"outputs":[{"execution_count":47,"output_type":"execute_result","data":{"text/plain":"","text/html":"\n \n "},"metadata":{}}],"execution_count":47}]}