whisper-at
by YuanGongND
Code and Pretrained Models for Interspeech 2023 Paper "Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong Audio Event Taggers"
AI summary
Audio tagger
An audio processing model that adds audio event tagging capabilities to an existing speech recognition system with minimal additional computational cost.
- stars
- 343
- forks
- 28
- watching
- 11
- awesome list
- 1
Similar projects
Found by comparing what the projects do, not just their names.
Audio Model
An audio and speech large language model implementation with pre-trained models, datasets, and inference options
Speech recog
Provides a high-performance speech recognition system for Unity3D applications.
Timestamped ASR
An extension to the Whisper speech recognition model that adds word-level timestamps and confidence scores.
ASR library
Provides an R interface to the Whisper Automatic Speech Recognition model
Audio tagging research
Research on end-to-end learning for music audio tagging using large datasets and different front-end paradigms.
Transcription engine
An implementation of Whisper's speech-to-text functionality in a real-time transcription application
Speech Recognizer
A Swift package for C implementation of a speech recognition system
Speech Recognizer Adapter
A tool for fine-tuning the OpenAI Whisper speech recognition model using residual adapters and parameter-efficient learning methods.
Audio metadata reader
A Python library for reading and extracting metadata from various audio file formats.
Syllable segmentation tool
An implementation of a score-informed method for segmenting jingju a cappella singing voice into syllables using convolutional neural networks and Viterbi algorithm
Audio-score matcher
This repository provides a software framework to match singing audio with corresponding music scores based on phonetic and duration information.
Video transcriber
Transcribes Youtube videos using OpenAI's Whisper speech recognition model
Audio perceptron
A large language model enabling speech, audio event perception and music inputs to achieve multilingual capabilities
Audio classifier
This project provides an implementation of a deep learning framework to classify audio signals and offers insights into the model's decision-making process using Explainable Artificial Intelligence (AI) techniques.
Music tagger
This project is an audio classification system trained on the MSD tagging dataset, enabling automatic tagging of music files with relevant genres and styles.
Featured in 1 awesome list
Each link jumps to the spot where the list mentions whisper-at.
