-
Tsinghua University
- China Beijing
Stars
LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.
open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.
Multi-Scale Neural Audio Codec (SNAC) compresses audio into discrete codes at a low bitrate
SOTA discrete acoustic codec models with 40 tokens per second for audio language modeling
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.
Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)
Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
SpeechGPT Series: Speech Large Language Models
Provides training, inference and voice conversion recipes for RADTTS and RADTTS++: Flow-based TTS models with Robust Alignment Learning, Diverse Synthesis, and Generative Modeling and Fine-Grained …
[InterSpeech 24] FreeV: Free Lunch For Vocoders Through Pseudo Inversed Mel Filter
How to use our public wav2vec2 dimensional emotion model
AcademiCodec: An Open Source Audio Codec Model for Academic Research
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Vector (and Scalar) Quantization, in Pytorch
A generative speech model for daily dialogue.
Audio Codec Speech processing Universal PERformance Benchmark
High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.
Instant voice cloning by MIT and MyShell.
Object-oriented handling of audio data, with GPU-powered augmentations, and more.
State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
[ICASSP 2024] This is the official code for "VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching"