Open-Source Turn-Taking Detection Model and Dataset for Full-Duplex Spoken Dialogue Systems

Text-audio foundation model from Boson AI

A Large-scale Cantonese Speech Corpus with Multi-dimensional Annotation

Causal streaming adaptation of OpenAI Whisper for real-time transcription on small audio chunks.

For audio visualization and playback in Jupyter notebooks.

Fully Native Swift and CoreML. Efficient Speaker Diarization, VAD, and Speech-to-Text for realtime workloads

CosyVoice_DPO_NOTES: Supercharge Your Cosyvoice model with Cutting-Edge DPO Fine-Tuning!

📚 从零开始的大语言模型原理与实践教程

low-latency realtime ASR based on FireRedASR

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

IndexTTS Fine-tuning notebooks

Self-supervised Generative LM-based Voice Conversion

使用vllm加速cosyvoice2的推理

Localized watermarking for AI-generated speech audios, with SOTA on robustness and very fast detector

[ACM MM'24] Coarse-to-Fine Proposal Refinement Framework for Audio Temporal Forgery Detection and Localization

A Survey of Spoken Dialogue Models (60 pages)

「大模型」3小时完全从0训练26M的小参数GPT，个人显卡即可推理训练！

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

SCOREQ: Speech COntrastive REgression for Quality Assessment (NeurIPS 2024)

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

Dataset and code of GTSinger(NeurIPS 2024 Spotlight): A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks

Official repository for Mamba-based Segmentation Model for Speaker Diarization

Open source inference code for Rev's model

Speech, Language, Audio, Music Processing with Large Language Model

SSR-Speech: Towards Stable, Safe and Robust Zero-shot Speech Editing and Synthesis

Automatically Update Text-to-speech (TTS) Papers Daily using Github Actions (Update Every 12th hours)