An Open Source Python alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI

📄 Configuration files that enhance Cursor AI editor experience with custom rules and behaviors

A high-throughput and memory-efficient inference and serving engine for LLMs

real time face swap and one-click video deepfake with only a single image

zero-vocab or low-vocab embeddings

Omni SenseVoice: High-Speed Speech Recognition with words timestamps 🗣️🎯

视频硬字幕提取，生成srt文件。无需申请第三方API，本地实现文本识别。基于深度学习的视频字幕提取框架，包含字幕区域检测、字幕内容提取。A GUI tool for extracting hard-coded subtitle (hardsub) from videos and generating srt files.

The Unofficial TikTok API Wrapper In Python

Sequence alignement methods with helpers for PyTorch.

FACodec: Speech Codec with Attribute Factorization used for NaturalSpeech 3

Audio Codec Speech processing Universal PERformance Benchmark

AudioLDM training, finetuning, evaluation and inference.

Audio generation using diffusion models, in PyTorch.

🔊 Text-prompted Generative Audio Model - With the ability to clone voices

PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

The DARPA TIMIT Acoustic-Phonetic Continuous Speech Corpus.

📝 Algorithms and data structures implemented in JavaScript with explanations and links to further readings