jd3655

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

soundstorm-pytorch

Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch

descript-audio-codec

State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

chatpdf

Chat and Ask on your own data. Accelerator to quickly upload your own enterprise data and use OpenAI services to chat to that uploaded data and ask questions

bark-voice-cloning-HuBERT-quantizer

The code for the bark-voicecloning model. Training and inference.

GPT4Tools

GPT4Tools is an intelligent system that can automatically decide, control, and utilize different visual foundation models, allowing the user to interact with images during a conversation.

knn-vc

Voice Conversion With Just Nearest Neighbors

vocos

Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis

landmark-attention

Landmark Attention: Random-Access Infinite Context Length for Transformers

mayavoz

Pytorch based speech enhancement toolkit.

XPhoneBERT

XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech (INTERSPEECH 2023)

Pengi

An Audio Language model for Audio Tasks

NS2VC

Unofficial implementation of NaturalSpeech2 for Voice Conversion and Text to Speech

spear-tts-pytorch

An unofficial PyTorch implementation of SPEAR-TTS.

PL-BERT

Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions

CoMoSpeech

CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model

DDDM-VC

Official Pytorch Implementation for "DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversion" (AAAI 2024)

efficientspeech

PyTorch code implementation of EfficientSpeech - to be presented at ICASSP2023.

NaturalSpeech2

Barkify

Barkify: an unoffical training implementation of Bark TTS by suno-ai

SpeechPrompt-v2

《SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks》Speech processing with prompting paradigm

NaturalSpeech2

zeus-llm-trainer

Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models

WaveODE

An ODE-based generative neural vocoder using Rectified Flow

NaturalSpeech2

tts-trainer

Generate audio datasets for training Text-To-Speech models, through smart audio splitting with silence detection, and transcription using Whisper.

audio-gen-dreambooth

fluenttts

FluentTTS: Text-dependent Fine-grained Style Control for Multi-style TTS

ArticulateAI

Listen, transcribe, reply - Voice Assistant using OpenAI & ElevenLabs API's

naturalspeech2-pytorch

Implementation of Natural Speech 2, Zero-shot Speech and Singing Synthesizer, in Pytorch