✨✨The First-Eval Open-Source Interactive Omni Multimodal LLM

SpeechGPT Series: Speech Large Language Models

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

ms-swift: Use PEFT or Full-parameter to finetune 250+ LLMs or 35+ MLLMs. (Qwen2, GLM4, Internlm2, Yi, Llama3, Llava, Deepseek, Baichuan2...)

A fast inference library for running LLMs locally on modern consumer-class GPUs

Transformer based ASR Engine.

Free and Open, Distributed, RESTful Search Engine

A playbook for systematically maximizing the performance of deep learning models.

Standalone implementation of the CUDA-accelerated WFST Decoder available in Riva

FSA/FST algorithms, intended to (eventually) be interoperable with PyTorch and similar

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

it's ASR decoder and make graph project

Acceptance rates for the major AI conferences

This is the implementation of paper CONSISTENT TRAINING AND DECODING FOR END-TO-END SPEECH RECOGNITIONUSING LATTICE-FREE MMI submitted to ICASSP2022

This is now the official location of the Kaldi project.

Towards hot directions in industrial speech recognition

Maix Speech AI lib, including ASR, chat, TTS etc.

NeMo: a toolkit for conversational AI

CUDA-Warp RNN-Transducer

A PyTorch-based Speech Toolkit

The RWTH ASR Toolkit.

A workspace for single/multi-channel speech recognition & enhancement & separation.

Fast parallel CTC.

Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo

a lightweight speech processing toolkit based on Pytorch and (Py)Kaldi

Pronunciation lexicon covering both English and Chinese languages for Automatic Speech Recognition.

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Espresso: A Fast End-to-End Neural Speech Recognition Toolkit