#
Starred repositories
Speech To Speech: an effort for an open-sourced and modular GPT4-o
The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.
VITS with phoneme-level prosody modeling based on MaskGIT
LlamaVoice is a llama-based large voice generation model, providing inference and training ability.
A project that optimizes Whisper for low latency inference using NVIDIA TensorRT
Localized watermarking for AI-generated speech audios, with SOTA on robustness and very fast detector
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
This repository contains audio samples and supplementary materials accompanying publications by the "Speaker, Voice and Language" team at Google.
Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper
Toolkit to segment text into sentences or other semantic units in a robust, efficient and adaptable way.
MARS5 speech model (TTS) from CAMB.AI
JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.
This is an implementation for train hifigan part of XTTSv2 model using Coqui/TTS.
A generative speech model for daily dialogue.
Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model
LIGHTVOC AN UPSAMPLING-FREE GAN VOCODER BASED ON CONFORMER AND INVERSE SHORT-TIME FOURIER TRANSFORM
Automatically Update Text-to-speech (TTS) Papers Daily using Github Actions (Update Every 12th hours)
High fidelity, lightweight, end-to-end, streaming, convolution-based neural audio codec
Open-source, accurate and easy-to-use video speech recognition & clipping tool, LLM based AI clipping intergrated.
Transcription, forced alignment, and audio indexing with OpenAI's Whisper