Awesome Neural Codec Models, Text-to-Speech Synthesizers & Speech Language Models

TTSAudioNormalizer is a specialized tool for TTS data production, featuring descriptive statistical analysis of audio loudness and loudness normalization operations.

《大语言模型》作者：赵鑫，李军毅，周昆，唐天一，文继荣

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

Collection of awesome LLM apps with RAG using OpenAI, Anthropic, Gemini and opensource models.

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Implementation of the CVPR 2019 Paper - Speech2Face: Learning the Face Behind a Voice by MIT CSAIL

Audio-Visual Speech Separation with Cross-Modal Consistency

A family of state-of-the-art Transformer-based audio codecs for low-bitrate high-quality audio coding.

Awesome speech/audio LLMs, representation learning, and codec models

A Survey of Spoken Dialogue Models (60 pages)

An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.

General Speech Restoration

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

Manipulate audio with a simple and easy high level interface

Code for the paper Hybrid Spectrogram and Waveform Source Separation

Noise supression using deep filtering

GUI for a Vocal Remover that uses Deep Neural Networks.

✨✨Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM

Accessible large language models via k-bit quantization for PyTorch.

汉字转拼音(pypinyin)

Paper, Code and Resources for Speech Language Model and End2End Speech Dialogue System.

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)

The official repo of NBC & SpatialNet for multichannel speech separation, denoising, and dereverberation

汉字拼音数据

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

GLM-4-Voice | 端到端中英语音对话模型

Continuation of Clash Verge - A Clash Meta GUI based on Tauri (Windows, MacOS, Linux)