{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[{"file_id":"1oggeLJuRhywdk0U3oLtSn4RI4OuqY3C8","timestamp":1685676269137}]},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"}},"cells":[{"cell_type":"code","execution_count":1,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":752},"id":"O3mwjxmyn81o","executionInfo":{"status":"ok","timestamp":1685677082601,"user_tz":-330,"elapsed":137429,"user":{"displayName":"Sulakshana Geeth","userId":"14781868669328079827"}},"outputId":"97f652a7-a9b4-4bd6-9682-a2317482ba68"},"outputs":[{"output_type":"stream","name":"stdout","text":["Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n","Requirement already satisfied: librosa in /usr/local/lib/python3.10/dist-packages (0.10.0.post2)\n","Requirement already satisfied: audioread>=2.1.9 in /usr/local/lib/python3.10/dist-packages (from librosa) (3.0.0)\n","Requirement already satisfied: numpy!=1.22.0,!=1.22.1,!=1.22.2,>=1.20.3 in /usr/local/lib/python3.10/dist-packages (from librosa) (1.22.4)\n","Requirement already satisfied: scipy>=1.2.0 in /usr/local/lib/python3.10/dist-packages (from librosa) (1.10.1)\n","Requirement already satisfied: scikit-learn>=0.20.0 in /usr/local/lib/python3.10/dist-packages (from librosa) (1.2.2)\n","Requirement already satisfied: joblib>=0.14 in /usr/local/lib/python3.10/dist-packages (from librosa) (1.2.0)\n","Requirement already satisfied: decorator>=4.3.0 in /usr/local/lib/python3.10/dist-packages (from librosa) (4.4.2)\n","Requirement already satisfied: numba>=0.51.0 in /usr/local/lib/python3.10/dist-packages (from librosa) (0.56.4)\n","Requirement already satisfied: soundfile>=0.12.1 in /usr/local/lib/python3.10/dist-packages (from librosa) (0.12.1)\n","Requirement already satisfied: pooch<1.7,>=1.0 in /usr/local/lib/python3.10/dist-packages (from librosa) (1.6.0)\n","Requirement already satisfied: soxr>=0.3.2 in /usr/local/lib/python3.10/dist-packages (from librosa) (0.3.5)\n","Requirement already satisfied: typing-extensions>=4.1.1 in /usr/local/lib/python3.10/dist-packages (from librosa) (4.5.0)\n","Requirement already satisfied: lazy-loader>=0.1 in /usr/local/lib/python3.10/dist-packages (from librosa) (0.2)\n","Requirement already satisfied: msgpack>=1.0 in /usr/local/lib/python3.10/dist-packages (from librosa) (1.0.5)\n","Requirement already satisfied: llvmlite<0.40,>=0.39.0dev0 in /usr/local/lib/python3.10/dist-packages (from numba>=0.51.0->librosa) (0.39.1)\n","Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from numba>=0.51.0->librosa) (67.7.2)\n","Requirement already satisfied: appdirs>=1.3.0 in /usr/local/lib/python3.10/dist-packages (from pooch<1.7,>=1.0->librosa) (1.4.4)\n","Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from pooch<1.7,>=1.0->librosa) (23.1)\n","Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/dist-packages (from pooch<1.7,>=1.0->librosa) (2.27.1)\n","Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=0.20.0->librosa) (3.1.0)\n","Requirement already satisfied: cffi>=1.0 in /usr/local/lib/python3.10/dist-packages (from soundfile>=0.12.1->librosa) (1.15.1)\n","Requirement already satisfied: pycparser in /usr/local/lib/python3.10/dist-packages (from cffi>=1.0->soundfile>=0.12.1->librosa) (2.21)\n","Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->pooch<1.7,>=1.0->librosa) (1.26.15)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->pooch<1.7,>=1.0->librosa) (2022.12.7)\n","Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->pooch<1.7,>=1.0->librosa) (2.0.12)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->pooch<1.7,>=1.0->librosa) (3.4)\n","Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n","Requirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (1.2.2)\n","Requirement already satisfied: numpy>=1.17.3 in /usr/local/lib/python3.10/dist-packages (from scikit-learn) (1.22.4)\n","Requirement already satisfied: scipy>=1.3.2 in /usr/local/lib/python3.10/dist-packages (from scikit-learn) (1.10.1)\n","Requirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-learn) (1.2.0)\n","Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn) (3.1.0)\n","Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n","Requirement already satisfied: joblib in /usr/local/lib/python3.10/dist-packages (1.2.0)\n","Accuracy: 1.0\n","Model saved as audio_classifier_model.pkl\n"]},{"output_type":"display_data","data":{"text/plain":["<IPython.core.display.HTML object>"],"text/html":["\n"," <input type=\"file\" id=\"files-be4855f8-e3d2-40f8-bb2f-b95b611cedd6\" name=\"files[]\" multiple disabled\n"," style=\"border:none\" />\n"," <output id=\"result-be4855f8-e3d2-40f8-bb2f-b95b611cedd6\">\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"," </output>\n"," <script>// Copyright 2017 Google LLC\n","//\n","// Licensed under the Apache License, Version 2.0 (the \"License\");\n","// you may not use this file except in compliance with the License.\n","// You may obtain a copy of the License at\n","//\n","// http://www.apache.org/licenses/LICENSE-2.0\n","//\n","// Unless required by applicable law or agreed to in writing, software\n","// distributed under the License is distributed on an \"AS IS\" BASIS,\n","// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n","// See the License for the specific language governing permissions and\n","// limitations under the License.\n","\n","/**\n"," * @fileoverview Helpers for google.colab Python module.\n"," */\n","(function(scope) {\n","function span(text, styleAttributes = {}) {\n"," const element = document.createElement('span');\n"," element.textContent = text;\n"," for (const key of Object.keys(styleAttributes)) {\n"," element.style[key] = styleAttributes[key];\n"," }\n"," return element;\n","}\n","\n","// Max number of bytes which will be uploaded at a time.\n","const MAX_PAYLOAD_SIZE = 100 * 1024;\n","\n","function _uploadFiles(inputId, outputId) {\n"," const steps = uploadFilesStep(inputId, outputId);\n"," const outputElement = document.getElementById(outputId);\n"," // Cache steps on the outputElement to make it available for the next call\n"," // to uploadFilesContinue from Python.\n"," outputElement.steps = steps;\n","\n"," return _uploadFilesContinue(outputId);\n","}\n","\n","// This is roughly an async generator (not supported in the browser yet),\n","// where there are multiple asynchronous steps and the Python side is going\n","// to poll for completion of each step.\n","// This uses a Promise to block the python side on completion of each step,\n","// then passes the result of the previous step as the input to the next step.\n","function _uploadFilesContinue(outputId) {\n"," const outputElement = document.getElementById(outputId);\n"," const steps = outputElement.steps;\n","\n"," const next = steps.next(outputElement.lastPromiseValue);\n"," return Promise.resolve(next.value.promise).then((value) => {\n"," // Cache the last promise value to make it available to the next\n"," // step of the generator.\n"," outputElement.lastPromiseValue = value;\n"," return next.value.response;\n"," });\n","}\n","\n","/**\n"," * Generator function which is called between each async step of the upload\n"," * process.\n"," * @param {string} inputId Element ID of the input file picker element.\n"," * @param {string} outputId Element ID of the output display.\n"," * @return {!Iterable<!Object>} Iterable of next steps.\n"," */\n","function* uploadFilesStep(inputId, outputId) {\n"," const inputElement = document.getElementById(inputId);\n"," inputElement.disabled = false;\n","\n"," const outputElement = document.getElementById(outputId);\n"," outputElement.innerHTML = '';\n","\n"," const pickedPromise = new Promise((resolve) => {\n"," inputElement.addEventListener('change', (e) => {\n"," resolve(e.target.files);\n"," });\n"," });\n","\n"," const cancel = document.createElement('button');\n"," inputElement.parentElement.appendChild(cancel);\n"," cancel.textContent = 'Cancel upload';\n"," const cancelPromise = new Promise((resolve) => {\n"," cancel.onclick = () => {\n"," resolve(null);\n"," };\n"," });\n","\n"," // Wait for the user to pick the files.\n"," const files = yield {\n"," promise: Promise.race([pickedPromise, cancelPromise]),\n"," response: {\n"," action: 'starting',\n"," }\n"," };\n","\n"," cancel.remove();\n","\n"," // Disable the input element since further picks are not allowed.\n"," inputElement.disabled = true;\n","\n"," if (!files) {\n"," return {\n"," response: {\n"," action: 'complete',\n"," }\n"," };\n"," }\n","\n"," for (const file of files) {\n"," const li = document.createElement('li');\n"," li.append(span(file.name, {fontWeight: 'bold'}));\n"," li.append(span(\n"," `(${file.type || 'n/a'}) - ${file.size} bytes, ` +\n"," `last modified: ${\n"," file.lastModifiedDate ? file.lastModifiedDate.toLocaleDateString() :\n"," 'n/a'} - `));\n"," const percent = span('0% done');\n"," li.appendChild(percent);\n","\n"," outputElement.appendChild(li);\n","\n"," const fileDataPromise = new Promise((resolve) => {\n"," const reader = new FileReader();\n"," reader.onload = (e) => {\n"," resolve(e.target.result);\n"," };\n"," reader.readAsArrayBuffer(file);\n"," });\n"," // Wait for the data to be ready.\n"," let fileData = yield {\n"," promise: fileDataPromise,\n"," response: {\n"," action: 'continue',\n"," }\n"," };\n","\n"," // Use a chunked sending to avoid message size limits. See b/62115660.\n"," let position = 0;\n"," do {\n"," const length = Math.min(fileData.byteLength - position, MAX_PAYLOAD_SIZE);\n"," const chunk = new Uint8Array(fileData, position, length);\n"," position += length;\n","\n"," const base64 = btoa(String.fromCharCode.apply(null, chunk));\n"," yield {\n"," response: {\n"," action: 'append',\n"," file: file.name,\n"," data: base64,\n"," },\n"," };\n","\n"," let percentDone = fileData.byteLength === 0 ?\n"," 100 :\n"," Math.round((position / fileData.byteLength) * 100);\n"," percent.textContent = `${percentDone}% done`;\n","\n"," } while (position < fileData.byteLength);\n"," }\n","\n"," // All done.\n"," yield {\n"," response: {\n"," action: 'complete',\n"," }\n"," };\n","}\n","\n","scope.google = scope.google || {};\n","scope.google.colab = scope.google.colab || {};\n","scope.google.colab._files = {\n"," _uploadFiles,\n"," _uploadFilesContinue,\n","};\n","})(self);\n","</script> "]},"metadata":{}},{"output_type":"stream","name":"stdout","text":["Saving futuristic-beat-146661.mp3 to futuristic-beat-146661.mp3\n","Predicted Label: autism\n"]}],"source":["!pip install librosa\n","!pip install scikit-learn\n","!pip install joblib\n","\n","\n","\n","\n","import os\n","import numpy as np\n","import librosa\n","from sklearn.model_selection import train_test_split\n","from sklearn.preprocessing import LabelEncoder\n","from sklearn.svm import SVC\n","from sklearn.metrics import accuracy_score\n","import joblib\n","\n","# Set the paths to your audio datasets\n","autism_folder = '/content/audio/autism'\n","non_autism_folder = '/content/audio/non autism'\n","\n","# Function to extract audio features using Librosa\n","def extract_features(file_path):\n"," audio, sr = librosa.load(file_path, sr=22050) # Load audio file\n"," features = librosa.feature.mfcc(y=audio, sr=sr) # Extract MFCC features\n"," features = np.mean(features.T, axis=0) # Take the mean of MFCC features\n"," return features\n","\n","# Load audio files and extract features\n","autism_files = os.listdir(autism_folder)\n","non_autism_files = os.listdir(non_autism_folder)\n","\n","X = [] # Feature vectors\n","y = [] # Labels\n","\n","for file in autism_files:\n"," file_path = os.path.join(autism_folder, file)\n"," features = extract_features(file_path)\n"," X.append(features)\n"," y.append('autism')\n","\n","for file in non_autism_files:\n"," file_path = os.path.join(non_autism_folder, file)\n"," features = extract_features(file_path)\n"," X.append(features)\n"," y.append('non autism')\n","\n","# Encode labels\n","label_encoder = LabelEncoder()\n","y = label_encoder.fit_transform(y)\n","\n","# Split the dataset into training and testing sets\n","X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n","\n","# Train a support vector machine (SVM) classifier\n","classifier = SVC(kernel='rbf', C=1.0, gamma='scale', random_state=42)\n","classifier.fit(X_train, y_train)\n","\n","# Evaluate the classifier\n","y_pred = classifier.predict(X_test)\n","accuracy = accuracy_score(y_test, y_pred)\n","print(\"Accuracy:\", accuracy)\n","\n","# Save the model\n","model_file = \"audio_classifier_model.pkl\"\n","joblib.dump(classifier, model_file)\n","print(\"Model saved as\", model_file)\n","\n","# Function to predict the label for a given audio file\n","def classify_audio(file_path):\n"," features = extract_features(file_path)\n"," features = np.array([features]) # Reshape for prediction\n"," label = label_encoder.inverse_transform(classifier.predict(features))[0]\n"," return label\n","\n","# Load the saved model\n","loaded_model = joblib.load(model_file)\n","\n","# Upload an audio file and classify it\n","from google.colab import files\n","\n","uploaded_file = files.upload()\n","audio_file_path = list(uploaded_file.keys())[0]\n","\n","predicted_label = classify_audio(audio_file_path)\n","print(\"Predicted Label:\", predicted_label)\n"]},{"cell_type":"code","source":[],"metadata":{"id":"Y8QtswiTvfgn"},"execution_count":null,"outputs":[]}]}
{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"authorship_tag":"ABX9TyN//kAorUssjRtRjm/BIpc2"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"}},"cells":[{"cell_type":"code","execution_count":2,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":1000},"id":"PTphXgZv5PxK","executionInfo":{"status":"ok","timestamp":1684901181065,"user_tz":-330,"elapsed":23218,"user":{"displayName":"Sulakshana Geeth","userId":"14781868669328079827"}},"outputId":"cd2eee86-b161-4a03-bf06-c41f1804155b"},"outputs":[{"output_type":"stream","name":"stdout","text":["Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n","Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (2.0.1+cu118)\n","Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.29.2)\n","Requirement already satisfied: gradio in /usr/local/lib/python3.10/dist-packages (3.32.0)\n","Requirement already satisfied: torchaudio in /usr/local/lib/python3.10/dist-packages (2.0.2+cu118)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch) (3.12.0)\n","Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from torch) (4.5.0)\n","Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch) (1.11.1)\n","Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch) (3.1)\n","Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch) (3.1.2)\n","Requirement already satisfied: triton==2.0.0 in /usr/local/lib/python3.10/dist-packages (from torch) (2.0.0)\n","Requirement already satisfied: cmake in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch) (3.25.2)\n","Requirement already satisfied: lit in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch) (16.0.5)\n","Requirement already satisfied: huggingface-hub<1.0,>=0.14.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.14.1)\n","Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (1.22.4)\n","Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers) (23.1)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (6.0)\n","Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2022.10.31)\n","Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers) (2.27.1)\n","Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.13.3)\n","Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers) (4.65.0)\n","Requirement already satisfied: aiofiles in /usr/local/lib/python3.10/dist-packages (from gradio) (23.1.0)\n","Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from gradio) (3.8.4)\n","Requirement already satisfied: altair>=4.2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (4.2.2)\n","Requirement already satisfied: fastapi in /usr/local/lib/python3.10/dist-packages (from gradio) (0.95.2)\n","Requirement already satisfied: ffmpy in /usr/local/lib/python3.10/dist-packages (from gradio) (0.3.0)\n","Requirement already satisfied: gradio-client>=0.2.4 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.2.5)\n","Requirement already satisfied: httpx in /usr/local/lib/python3.10/dist-packages (from gradio) (0.24.1)\n","Requirement already satisfied: markdown-it-py[linkify]>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.2.0)\n","Requirement already satisfied: markupsafe in /usr/local/lib/python3.10/dist-packages (from gradio) (2.1.2)\n","Requirement already satisfied: matplotlib in /usr/local/lib/python3.10/dist-packages (from gradio) (3.7.1)\n","Requirement already satisfied: mdit-py-plugins<=0.3.3 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.3.3)\n","Requirement already satisfied: orjson in /usr/local/lib/python3.10/dist-packages (from gradio) (3.8.13)\n","Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from gradio) (1.5.3)\n","Requirement already satisfied: pillow in /usr/local/lib/python3.10/dist-packages (from gradio) (8.4.0)\n","Requirement already satisfied: pydantic in /usr/local/lib/python3.10/dist-packages (from gradio) (1.10.7)\n","Requirement already satisfied: pydub in /usr/local/lib/python3.10/dist-packages (from gradio) (0.25.1)\n","Requirement already satisfied: pygments>=2.12.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.14.0)\n","Requirement already satisfied: python-multipart in /usr/local/lib/python3.10/dist-packages (from gradio) (0.0.6)\n","Requirement already satisfied: semantic-version in /usr/local/lib/python3.10/dist-packages (from gradio) (2.10.0)\n","Requirement already satisfied: uvicorn>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.22.0)\n","Requirement already satisfied: websockets>=10.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (11.0.3)\n","Requirement already satisfied: entrypoints in /usr/local/lib/python3.10/dist-packages (from altair>=4.2.0->gradio) (0.4)\n","Requirement already satisfied: jsonschema>=3.0 in /usr/local/lib/python3.10/dist-packages (from altair>=4.2.0->gradio) (4.3.3)\n","Requirement already satisfied: toolz in /usr/local/lib/python3.10/dist-packages (from altair>=4.2.0->gradio) (0.12.0)\n","Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from gradio-client>=0.2.4->gradio) (2023.4.0)\n","Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py[linkify]>=2.0.0->gradio) (0.1.2)\n","Requirement already satisfied: linkify-it-py<3,>=1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py[linkify]>=2.0.0->gradio) (2.0.2)\n","Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->gradio) (2.8.2)\n","Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->gradio) (2022.7.1)\n","Requirement already satisfied: click>=7.0 in /usr/local/lib/python3.10/dist-packages (from uvicorn>=0.14.0->gradio) (8.1.3)\n","Requirement already satisfied: h11>=0.8 in /usr/local/lib/python3.10/dist-packages (from uvicorn>=0.14.0->gradio) (0.14.0)\n","Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio) (23.1.0)\n","Requirement already satisfied: charset-normalizer<4.0,>=2.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio) (2.0.12)\n","Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio) (6.0.4)\n","Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio) (4.0.2)\n","Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio) (1.9.2)\n","Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio) (1.3.3)\n","Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio) (1.3.1)\n","Requirement already satisfied: starlette<0.28.0,>=0.27.0 in /usr/local/lib/python3.10/dist-packages (from fastapi->gradio) (0.27.0)\n","Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx->gradio) (2022.12.7)\n","Requirement already satisfied: httpcore<0.18.0,>=0.15.0 in /usr/local/lib/python3.10/dist-packages (from httpx->gradio) (0.17.2)\n","Requirement already satisfied: idna in /usr/local/lib/python3.10/dist-packages (from httpx->gradio) (3.4)\n","Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from httpx->gradio) (1.3.0)\n","Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio) (1.0.7)\n","Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio) (0.11.0)\n","Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio) (4.39.3)\n","Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio) (1.4.4)\n","Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio) (3.0.9)\n","Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (1.26.15)\n","Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch) (1.3.0)\n","Requirement already satisfied: anyio<5.0,>=3.0 in /usr/local/lib/python3.10/dist-packages (from httpcore<0.18.0,>=0.15.0->httpx->gradio) (3.6.2)\n","Requirement already satisfied: pyrsistent!=0.17.0,!=0.17.1,!=0.17.2,>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair>=4.2.0->gradio) (0.19.3)\n","Requirement already satisfied: uc-micro-py in /usr/local/lib/python3.10/dist-packages (from linkify-it-py<3,>=1->markdown-it-py[linkify]>=2.0.0->gradio) (1.0.2)\n","Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas->gradio) (1.16.0)\n"]},{"output_type":"stream","name":"stderr","text":["Some weights of the model checkpoint at jonatasgrosman/wav2vec2-large-xlsr-53-english were not used when initializing Wav2Vec2ForSequenceClassification: ['lm_head.bias', 'lm_head.weight']\n","- This IS expected if you are initializing Wav2Vec2ForSequenceClassification 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 Wav2Vec2ForSequenceClassification 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 Wav2Vec2ForSequenceClassification were not initialized from the model checkpoint at jonatasgrosman/wav2vec2-large-xlsr-53-english and are newly initialized: ['projector.bias', 'projector.weight', 'classifier.bias', 'classifier.weight']\n","You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n","/usr/local/lib/python3.10/dist-packages/gradio/inputs.py:321: UserWarning: Usage of gradio.inputs is deprecated, and will not be supported in the future, please import your components from gradio.components\n"," warnings.warn(\n","/usr/local/lib/python3.10/dist-packages/gradio/inputs.py:324: UserWarning: `optional` parameter is deprecated, and it has no effect\n"," super().__init__(source=source, type=type, label=label, optional=optional)\n","/usr/local/lib/python3.10/dist-packages/gradio/outputs.py:22: UserWarning: Usage of gradio.outputs is deprecated, and will not be supported in the future, please import your components from gradio.components\n"," warnings.warn(\n"]},{"output_type":"stream","name":"stdout","text":["Colab notebook detected. To show errors in colab notebook, set debug=True in launch()\n","Note: opening Chrome Inspector may crash demo inside Colab notebooks.\n","\n","To create a public link, set `share=True` in `launch()`.\n"]},{"output_type":"display_data","data":{"text/plain":["<IPython.core.display.Javascript object>"],"application/javascript":["(async (port, path, width, height, cache, element) => {\n"," if (!google.colab.kernel.accessAllowed && !cache) {\n"," return;\n"," }\n"," element.appendChild(document.createTextNode(''));\n"," const url = await google.colab.kernel.proxyPort(port, {cache});\n","\n"," const external_link = document.createElement('div');\n"," external_link.innerHTML = `\n"," <div style=\"font-family: monospace; margin-bottom: 0.5rem\">\n"," Running on <a href=${new URL(path, url).toString()} target=\"_blank\">\n"," https://localhost:${port}${path}\n"," </a>\n"," </div>\n"," `;\n"," element.appendChild(external_link);\n","\n"," const iframe = document.createElement('iframe');\n"," iframe.src = new URL(path, url).toString();\n"," iframe.height = height;\n"," iframe.allow = \"autoplay; camera; microphone; clipboard-read; clipboard-write;\"\n"," iframe.width = width;\n"," iframe.style.border = 0;\n"," element.appendChild(iframe);\n"," })(7861, \"/\", \"100%\", 500, false, window.element)"]},"metadata":{}},{"output_type":"execute_result","data":{"text/plain":[]},"metadata":{},"execution_count":2}],"source":["!pip install torch transformers gradio torchaudio\n","\n","import torch\n","from transformers import Wav2Vec2Processor, Wav2Vec2ForSequenceClassification\n","import torchaudio\n","import numpy as np\n","import gradio as gr\n","\n","# Step 1: Define the speaking tone classification model\n","model_name = \"jonatasgrosman/wav2vec2-large-xlsr-53-english\"\n","processor = Wav2Vec2Processor.from_pretrained(model_name)\n","model = Wav2Vec2ForSequenceClassification.from_pretrained(model_name)\n","\n","# Step 2: Create a function to analyze the speaking tone\n","def analyze_speaking_tone(audio):\n"," try:\n"," waveform, sample_rate = torchaudio.load(audio)\n"," input_values = processor(waveform, return_tensors=\"pt\").input_values\n"," attention_mask = torch.ones_like(input_values)\n","\n"," with torch.no_grad():\n"," outputs = model(input_values=input_values, attention_mask=attention_mask)\n","\n"," predicted_label = torch.argmax(outputs.logits).item()\n"," if predicted_label == 1:\n"," speaking_tone = \"Abnormal\"\n"," else:\n"," speaking_tone = \"Normal\"\n","\n"," return speaking_tone\n"," except Exception as e:\n"," recommendation = \"An error occurred while analyzing the speaking tone. Please try the following steps:\\n\\n1. Ensure that the audio input is in a valid format.\\n2. Check the quality and clarity of the audio.\\n3. Adjust the preprocessing techniques such as noise reduction or audio normalization.\\n4. Retrain the speaking tone classification model using a diverse and high-quality audio dataset.\\n\\nIf the issue persists, please consult with a domain expert or seek technical support.\"\n"," return recommendation\n","\n","# Step 3: Create a Gradio interface to interact with the model\n","audio_input = gr.inputs.Audio(label=\"Audio\", type=\"numpy\")\n","tone_output = gr.outputs.Textbox(label=\"Speaking Tone\")\n","\n","iface = gr.Interface(fn=analyze_speaking_tone, inputs=audio_input, outputs=tone_output)\n","iface.launch()\n"]}]}
