Code and pretrained models for "DUB: Discrete Unit Back-translation for Speech Translation" (ACL 2023 Findings)

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

A PyTorch-based Speech Toolkit

[CVPR 2024] AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation

A curated list of awesome voice conversion, projects and communities.

Unified-Modal Speech-Text Pre-Training for Spoken Language Processing

[TASLP 2024] Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation

Foundational Models for State-of-the-Art Speech and Text Translation

Prosodic Speech Segmentation with Transformers

🌈 Github colors for all the languages

Minimal, responsive Jekyll theme for hackers

User-friendly WebUI for AI (Formerly Ollama WebUI)

Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.

C++ associative containers

A neural word aligner based on multilingual BERT

MessagePack implementation for C and C++ / msgpack.org[C/C++]

Universal cross-platform tokenizers binding to HF and sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

PyTorch original implementation of Cross-lingual Language Model Pretraining.

This tool helps automatic generation of grammatically valid synthetic Code-mixed data by utilizing linguistic theories such as Equivalence Constant Theory and Matrix Language Theory.

Simple, fast unsupervised word aligner

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)