tincans-ai / gazelle
Joint speech-language model - respond directly to audio!
☆312Updated 2 months ago
Related projects: ⓘ
- ☆181Updated 3 months ago
- Llama3.1 learns to Listen☆134Updated this week
- ☆241Updated 3 months ago
- FastMLX is a high performance production ready API to host MLX models.☆163Updated last week
- Whisper with Medusa heads☆774Updated last week
- ☆244Updated 6 months ago
- A fast multimodal LLM for real-time voice☆847Updated this week
- Video+code lecture on building nanoGPT from scratch☆64Updated 3 months ago
- ☆149Updated last year
- On-device intelligence.☆136Updated last week
- A ggml (C++) re-implementation of tortoise-tts☆147Updated 3 weeks ago
- Convenience scripts to finetune (chat-)LLaMa3 and other models for any language☆260Updated 3 months ago
- Phi-3.5 for Mac: Locally-run Vision and Language Models for Apple Silicon☆206Updated last week
- An extremely fast implementation of whisper optimized for Apple Silicon using MLX.☆519Updated 4 months ago
- MLX-VLM is a package for running Vision LLMs locally on your Mac using MLX.☆187Updated this week
- A WebRTC server that allows you to interact with an LLM using your speech and responds back with generated audio.☆94Updated 3 months ago
- Embed arbitrary modalities (images, audio, documents, etc) into large language models.☆170Updated 5 months ago
- An mlx project to train a base model on your whatsapp chats using (Q)Lora finetuning☆156Updated 8 months ago
- Maybe the new state of the art vision model? we'll see 🤷♂️☆153Updated 8 months ago
- Start a server from the MLX library.☆157Updated last month
- run paligemma in real time☆122Updated 4 months ago
- Speech recognition & diarisation solution with text alignment, deployed in AML pipelines☆81Updated 4 months ago
- ☆453Updated 3 months ago
- ☆640Updated this week
- An Optimized Speech-to-Text Pipeline for the Whisper Model Supporting Multiple Inference Engine☆276Updated 3 weeks ago
- A fast, light, open chat UI with full tool use support across many models☆194Updated this week
- A comprehensive repository of reasoning tasks for LLMs (and beyond)☆260Updated last month
- Use late-interaction multi-modal models such as ColPali in just a few lines of code.☆318Updated this week
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆217Updated 6 months ago
- A fast batching API to serve LLM models☆172Updated 4 months ago