Aratako/Irodori-TTS
A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control
A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control
OpenAI Text-to-Speech API compatible server for Irodori-TTS
Inference server for MioTTS, a lightweight and fast LLM-based TTS model.
Multilingual TTS model with voice cloning and duration control, based on T5Gemma encoder-decoder LLM
An attempt to reproduce CALM (Continuous Audio Language Models) using DACVAE as the audio VAE.
シンプルなLlasaの推論サーバー
Magpieという手法とNemotron-4-340B-Instructを用いて合成対話データセットを作るコード
Common recipes to run vLLM
very fast speech-to-text, diarization, streaming (even in CPU) with NVIDIA Parakeet in Rust
Utils for Unsloth https://github.com/unslothai/unsloth
Tools for merging pretrained large language models.
Train transformer language models with reinforcement learning.
Easy to use stem (e.g. instrumental/vocals) separation from CLI or as a python package, using a variety of amazing pre-trained models (primarily from UVR)
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Project of llm evaluation to Japanese tasks
Demonstration of how to leverage Azure OpenAI and Cognitive Search to enable Information Search and Discovery over organizational content
Leveraging BERT and c-TF-IDF to create easily interpretable topics.
⚡ Building applications with LLMs through composability ⚡