🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Your offline, privacy-first voice assistant framework. Transform speech into commands and actions with a powerful, scriptable rule engine.

A video analysis application that helps students, educators, and professionals analyze presentations by combining speech transcription, visual analysis, and AI-powered feedback. The app processes videos to provide actionable insights on speaking performance, visual effectiveness, and overall presentation quality.

Blazing fast whisper turbo for ASR (speech-to-text) tasks

A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-friendly solution for running MLX-based vision and language models locally with an OpenAI-compatible interface.

Open-source voice data collection platform for building inclusive voice datasets. Collaborative transcription with quality consensus. FastAPI + React + PostgreSQL.

Improve pronunciation with real-time AI feedback

🔊 Train audio models efficiently with MiMo-Audio-Training, a toolkit designed for straightforward implementation and enhanced performance in audio processing tasks.

🎤 Control your world with Jarvis, a voice-activated AI assistant that simplifies tasks and enhances productivity.

📚 Transform learning with TatvaX, an AI platform providing personalized education in 8 Indian languages, breaking down language barriers for millions.

🎤 Transform spoken phrases into OWL ontologies, making it easy to create structured data from voice. Ideal for developers and researchers alike.

🤖 Learn motion imitation with MimicKit, a framework offering advanced methods to train motion controllers using state-of-the-art algorithms and techniques.

🔊 Evaluate audio performance with the MiMo-Audio-Eval toolkit, designed for accurate assessment and streamlined analysis in audio processing tasks.

🎤 Convert Bangla audio files to text accurately with BanglaSTT, a cross-platform speech-to-text tool powered by OpenAI Whisper.

📄 Generate and fine-tune large language models on Apple silicon effortlessly with MLX LM, integrating seamlessly with the Hugging Face Hub.

🎤 Enhance speech recognition by detecting emotions in spoken language, combining OpenAI's Whisper and emotion analysis for deeper insights.

🗣️ Align audio with text seamlessly on macOS, generating accurate timestamps and subtitles in multiple formats for better accessibility.

🛠️ Train diffusion models with ease using this all-in-one toolkit, designed for image and video on consumer-grade hardware. Run it as a GUI or CLI.

📑 Explore WenetSpeech-Yue, a comprehensive Cantonese speech corpus with rich annotations, designed for advancing speech recognition research.

End-to-End Speech Processing Toolkit