A family of efficient speech models for multilingual phone recognition

Faker is a Python package that generates fake data for you.

Efficient Triton Kernels for LLM Training

Machine Learning Containers for NVIDIA Jetson and JetPack-L4T

A safetensors extension to efficiently store sparse quantized tensors on disk

FSA/FST algorithms, differentiable, with PyTorch compatibility.

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

Whisper realtime streaming for long speech-to-text transcription and translation

Silero Models: pre-trained text-to-speech models made embarrassingly simple

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

This is the code and dataset repo for Interspeech 2024 paper "Target conversation extraction: Source separation using turn-taking dynamics"

A high-throughput and memory-efficient inference and serving engine for LLMs

The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.

Prepend universal audio attack segment to mute Whisper

This repository contains the SpeechBrain Benchmarks

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

MLX: An array framework for Apple silicon

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Reference code for the paper The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translation.

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Repository for Accent Recognition (Hackathon @SLT2022)

SHAS: Approaching optimal Segmentation for End-to-End Speech Translation

text window manager, shell multiplexer, integrated DevOps environment

Acceptance rates for the major AI conferences

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)

A Corpus for Research on Robust Automatic Speech Recognition and Natural Language Understanding of Air Traffic Control Communications

Repository for sharing the data in the Tamasheq language, one of the target languages for the low-resource speech translation track at IWSLT2022.