Unified Pre-training for Self-Supervised Learning and Supervised Learning for ASR

Last update: Jan 09, 2023

Related tags

Overview

UniSpeech

The family of UniSpeech:

UniSpeech (ICML 2021): Unified Pre-training for Self-Supervised Learning and Supervised Learning for ASR

UniSpeech-SAT (ICASSP 2022 Submission): Universal Speech Representation Learning with Speaker Aware Pre-Training

Pre-trained models

We strongly suggest using our UniSpeech-SAT model for speaker related tasks, since it shows very powerful performance on various speaker related benchmarks.

Model	Dataset	Model
UniSpeech Base	1500 hrs CommonVoice	download
UniSpeech Large	1500 hrs CommonVoice	download
UniSpeech-SAT Base	960 hrs LibriSpeech	download
UniSpeech-SAT Base+	60k hrs Libri-Light + 10k hrs GigaSpeech + 24k hrs VoxPopuli	download
UniSpeech-SAT Large	60k hrs Libri-Light + 10k hrs GigaSpeech + 24k hrs VoxPopuli	download

License

This project is licensed under the license found in the LICENSE file in the root directory of this source tree. Portions of the source code are based on the FAIRSEQ project.

Microsoft Open Source Code of Conduct

Contact Information

For help or issues using UniSpeech models, please submit a GitHub issue.

For other communications related to UniSpeech, please contact Yu Wu ([email protected]).

Unified Pre-training for Self-Supervised Learning and Supervised Learning for ASR

Related tags

Overview

UniSpeech

Pre-trained models

License

Contact Information

Owner

Microsoft

Exploring Visual Engagement Signals for Representation Learning

Creating a custom CNN hypertunned architeture for the Fashion MNIST dataset with Python, Keras and Tensorflow.

This is a repository for a No-Code object detection inference API using the OpenVINO. It's supported on both Windows and Linux Operating systems.

Download & Install mods for your favorit game with a few simple clicks

A Differentiable Recipe for Learning Visual Non-Prehensile Planar Manipulation

Awesome Remote Sensing Toolkit based on PaddlePaddle.

UniMoCo: Unsupervised, Semi-Supervised and Full-Supervised Visual Representation Learning

Few-Shot Object Detection via Association and DIscrimination

Final project code: Implementing MAE with downscaled encoders and datasets, for ESE546 FA21 at University of Pennsylvania

ManimML is a project focused on providing animations and visualizations of common machine learning concepts with the Manim Community Library.

The implementation for paper Joint t-SNE for Comparable Projections of Multiple High-Dimensional Datasets.

Code for the Population-Based Bandits Algorithm, presented at NeurIPS 2020.

TensorFlow GNN is a library to build Graph Neural Networks on the TensorFlow platform.

Anomaly detection related books, papers, videos, and toolboxes

The implementation for "Comprehensive Knowledge Distillation with Causal Intervention".

Official code for paper Exemplar Based 3D Portrait Stylization.

[ICML'21] Estimate the accuracy of the classifier in various environments through self-supervision

Code for paper "Context-self contrastive pretraining for crop type semantic segmentation"

Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

cl;asification problem using classification models in supervised learning