{"id":22854698,"url":"https://github.com/alihassanml/speech-recognition-system","last_synced_at":"2025-03-31T07:22:13.937Z","repository":{"id":266119272,"uuid":"897448542","full_name":"alihassanml/Speech-Recognition-System","owner":"alihassanml","description":"This project implements a speech recognition system using the LibriSpeech dataset and the `librosa` library for feature extraction, alongside a deep learning model built with TensorFlow/Keras.","archived":false,"fork":false,"pushed_at":"2024-12-02T16:48:49.000Z","size":477,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-06T11:57:00.155Z","etag":null,"topics":["deep-learning","librosa","speech-recognition","speech-to-text"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/alihassanml.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-12-02T16:42:13.000Z","updated_at":"2024-12-02T16:49:24.000Z","dependencies_parsed_at":"2024-12-07T06:02:40.707Z","dependency_job_id":null,"html_url":"https://github.com/alihassanml/Speech-Recognition-System","commit_stats":null,"previous_names":["alihassanml/speech-recognition-system"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alihassanml%2FSpeech-Recognition-System","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alihassanml%2FSpeech-Recognition-System/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alihassanml%2FSpeech-Recognition-System/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alihassanml%2FSpeech-Recognition-System/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/alihassanml","download_url":"https://codeload.github.com/alihassanml/Speech-Recognition-System/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246429647,"owners_count":20775860,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","librosa","speech-recognition","speech-to-text"],"created_at":"2024-12-13T07:08:08.159Z","updated_at":"2025-03-31T07:22:13.916Z","avatar_url":"https://github.com/alihassanml.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Speech Recognition System\n\nThis project implements a speech recognition system using the LibriSpeech dataset and the `librosa` library for feature extraction, alongside a deep learning model built with TensorFlow/Keras.\n\n---\n\n## Table of Contents\n- [Overview](#overview)\n- [Features](#features)\n- [Installation](#installation)\n- [Usage](#usage)\n- [Model Architecture](#model-architecture)\n- [Dataset](#dataset)\n- [Results](#results)\n- [Contributing](#contributing)\n- [License](#license)\n\n---\n\n## Overview\nThis speech recognition system is designed to process audio files, extract meaningful features, and train a deep learning model using LSTMs to predict sequences. The project leverages the LibriSpeech dataset and the `librosa` library for audio analysis.\n\n---\n\n## Features\n- Audio preprocessing and feature extraction using `librosa`.\n- LSTM-based sequence model for speech recognition.\n- End-to-end training pipeline with data preprocessing, model training, and evaluation.\n\n---\n\n## Installation\nClone the repository and install the required dependencies:\n\n```bash\ngit clone https://github.com/alihassanml/Speech-Recognition-System.git\ncd Speech-Recognition-System\npip install -r requirements.txt\n```\n\n---\n\n## Usage\n1. **Preprocess Data**: Extract MFCC features using `librosa`.\n2. **Train Model**: Train the LSTM model with your processed dataset.\n3. **Evaluate Performance**: Test the trained model on unseen audio samples.\n\n### Feature Extraction Example\n```python\nimport librosa\nimport numpy as np\n\naudio_path = 'path_to_audio_file.wav'\ny, sr = librosa.load(audio_path, sr=None)\nmfcc = librosa.feature.mfcc(y=y, sr=sr, n_mfcc=20)\n```\n\n### Model Training Example\n```python\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, LSTM, Dropout\n\nmodel = Sequential()\nmodel.add(LSTM(128, return_sequences=True, input_shape=(length, 20)))\nmodel.add(Dropout(0.2))\nmodel.add(LSTM(128, return_sequences=True))\nmodel.add(Dropout(0.2))\nmodel.add(LSTM(128))\nmodel.add(Dropout(0.2))\nmodel.add(Dense(num_classes, activation='softmax'))\n\nmodel.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\nmodel.summary()\n```\n\n---\n\n## Model Architecture\nThe model is built using a stack of LSTMs with dropout layers to prevent overfitting. The architecture is as follows:\n- **LSTM (128 units)**: Captures temporal dependencies in the feature sequences.\n- **Dropout (20%)**: Regularization to reduce overfitting.\n- **Dense Layer**: Final layer with a softmax activation for classification.\n\n---\n\n## Dataset\n- **LibriSpeech**: A large-scale corpus of English speech data.\n- Download and preprocess the dataset using your preferred method.\n\n---\n\n## Results\nAdd your training accuracy, evaluation metrics, or sample predictions here.\n\n---\n\n## Contributing\nContributions are welcome! Please fork the repository, create a branch, and submit a pull request.\n\n---\n\n## License\nThis project is licensed under the MIT License.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falihassanml%2Fspeech-recognition-system","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falihassanml%2Fspeech-recognition-system","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falihassanml%2Fspeech-recognition-system/lists"}