🔊 Text-Prompted Generative Audio Model

CS229 Final Project

Defending against Adversarial Audio via Diffusion Model (ICLR 2023)

fine-tune Whipser model for Taiwanese speech recognition

Replace arXiv links by their corresponding bibliography in markdowns / Notion database

Faster Whisper transcription with CTranslate2

Transcribe a Collection of Waveform Audio Files using whisper_timestamped

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

A not very efficient attempt to create a real time openai/whisper (Audio to Text Transcriber)

Phoneme Recognition using pre-trained models Wav2vec2, HuBERT and WavLM. Throughout this project, we compared specifically three different self-supervised models, Wav2vec (2019, 2020), HuBERT (2021…

Physical Symbolic Optimization

📖 Paper reading list in conversational AI (constantly updating 🤗).

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Implementation of Bit Diffusion, Hinton's group's attempt at discrete denoising diffusion, in Pytorch

chinese speech pretrained models

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Transcribing Speech with Multinomial Diffusion, training code and models.

Revisiting Denoising Diffusion Probabilistic Models for Speech Enhancement: Condition Collapse, Efficiency and Refinement, Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI), 2023.

PyTorch implementation of the Perceptual Evaluation of Speech Quality for wideband audio

Trainer for audio-diffusion-pytorch

Code for a paper exploring using diffusion models to defend neural networks against adversarial attacks

Domain adaptation made easy. Fully featured, modular, and customizable.