alvanli/canto-audio-llm

stars

commits

Python

primary language

Jan 10, 2025

updated

README

this is an attempt in replicating the DiVA paper and finetune it to Cantonese audio data
- DiVA provides an easy way to create Audio models without generating a bunch of tasks for audio data, and without instruction data
- the original code was written in Levanter, so I wanted to turn it into PyTorch
The scripts are run on local Ubuntu machine with 2 x 4090s
The model has been training since Dec 19, 2024. When completed, results will be uploaded

18 commits

WillHeld/DiVA-llama-3-v0-8b

ChristianHinge/danstral

kehanlu/DeSTA2.5-Audio

Code for DeSTA2.5-Audio, general-purpose LALM

143

liuhuadai/AudioLCM

PyTorch Implementation of [AudioLCM]: a efficient and high-quality text-to-audio generation with…

Text-to-Audio/AudioLCM

PyTorch Implementation of AudioLCM (ACM-MM'24): a efficient and high-quality text-to-audio…

1,164

WangHelin1997/SoloAudio

SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer.

124

glory20h/VoiceLDM

VoiceLDM: Text-to-Speech with Environmental Context

194

Text-to-Audio/Make-An-Audio

PyTorch Implementation of Make-An-Audio (ICML'23) with a Text-to-Audio Generative Model

668

Python

99.2%

README

this is an attempt in replicating the DiVA paper and finetune it to Cantonese audio data
- DiVA provides an easy way to create Audio models without generating a bunch of tasks for audio data, and without instruction data
- the original code was written in Levanter, so I wanted to turn it into PyTorch
The scripts are run on local Ubuntu machine with 2 x 4090s
The model has been training since Dec 19, 2024. When completed, results will be uploaded