facebookresearch / libri-lightLinks
dataset for lightly supervised training using the librivox audio book recordings. https://librivox.org/.
☆505Updated 2 years ago
Alternatives and similar repositories for libri-light
Users that are interested in libri-light are comparing it to the libraries listed below
Sorting:
- A large-scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation☆551Updated 2 years ago
- UniSpeech - Large Scale Self-Supervised Learning for Speech☆468Updated last year
- Large, modern dataset for speech recognition☆692Updated last year
- A library for speech data augmentation in time-domain☆668Updated 3 years ago
- A Survey on Neural Speech Synthesis https://arxiv.org/pdf/2106.15561.pdf☆369Updated 3 years ago
- Segment an audio file and obtain utterance alignments. (Python package)☆339Updated last year
- Library for Textless Spoken Language Processing☆549Updated last year
- An official reimplementation of the method described in the INTERSPEECH 2021 paper - Speech Resynthesis from Discrete Disentangled Self-S…☆408Updated last year
- A fast and lightweight python-based CTC beam search decoder for speech recognition.☆456Updated 2 years ago
- Word alignments generated by the Montreal Forced Aligner for the Librispeech dataset☆167Updated 6 years ago
- This repository contains audio samples and supplementary materials accompanying publications by the "Speaker, Voice and Language" team at…☆425Updated last week
- VQ-VAE for Acoustic Unit Discovery and Voice Conversion☆338Updated 2 years ago
- A PyTorch implementation of Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis☆368Updated 2 years ago
- CoVoST: A Large-Scale Multilingual Speech-To-Text Translation Corpus (CC0 Licensed)☆386Updated 3 years ago
- Implementation of "MOSNet: Deep Learning based Objective Assessment for Voice Conversion"☆375Updated last year
- Grapheme to phoneme conversion with deep learning.☆394Updated last year
- CSS10: A Collection of Single Speaker Speech Datasets for 10 Languages☆474Updated 5 years ago
- The SpeechBrain project aims to build a novel speech toolkit fully based on PyTorch. With SpeechBrain users can easily create speech proc…☆370Updated 2 months ago
- ☆259Updated 2 years ago
- PyTorch Implementation of FastSpeech 2 : Fast and High-Quality End-to-End Text to Speech☆229Updated 3 years ago
- Speaker embedding (d-vector) trained with GE2E loss