Audio Captioning datasets for PyTorch.

Align Anything: Training All-modality Model with Feedback

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

Sample Repository for the AlibabaCloud Bailian Speech SDK

Awesome Neural Codec Models, Text-to-Speech Synthesizers & Speech Language Models

值得关注的中文twitter用户

so-vits-svc fork with realtime support, improved interface and more features.

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

An official reimplementation of the method described in the INTERSPEECH 2021 paper - Speech Resynthesis from Discrete Disentangled Self-Supervised Representations.

An official reimplementation of the method described in the INTERSPEECH 2021 paper - Speech Resynthesis from Discrete Disentangled Self-Supervised Representations.

VoiceBench: Benchmarking LLM-Based Voice Assistants

Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deplo…

【三年面试五年模拟】AI算法工程师面试秘籍。涵盖AIGC、传统深度学习、自动驾驶、机器学习、计算机视觉、自然语言处理、强化学习、具身智能、元宇宙、AGI等AI行业面试笔试经验与干货知识。

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

SALMONN: Speech Audio Language Music Open Neural Network

LLM101n: Let's build a Storyteller

Sample code for the Microsoft Cognitive Services Speech SDK

The official GitHub page for the survey paper "A Survey of Large Language Models".

Unoffical implementation of Megatts2

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

A one-stop data processing system to make data higher-quality, juicier, and more digestible for LLMs! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大语言模型提供更高质量、更丰富、更易”消化“的数据！

Mobile-Agent: The Powerful Mobile Device Operation Assistant Family

Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversation

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

Manipulate audio with a simple and easy high level interface