Google Gemini live voice to text realtime stream in the browser

A Constrained LearnLM Tutor

A Conversational Speech Generation Model

A simple interface for the CMU pronouncing dictionary

Audio Large Language Models

Near-Realtime audio transcription using self-hosted Whisper and WebSocket in Python/JS

Phoneme-based transformer training

Ultra-Lightweight Durable Execution in Python

An Open Source implementation of Notebook LM with more flexibility and features

An Open Source Python alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI

Creating Container Images in AWS Fargate with Kaniko

24/7 voice help for the homeless on Oahu -- call (808) 515-6625 or:

Extract frequency, power, width and dissonance of formants from wav files

A no-code instructional role-playing game generator with voice I/O on Vapi

[ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation

A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 37.3% tasks (pass@1) in SWE-bench lite and 46.2% tasks (pass@1) in SWE-bench verified with…

Public area for Speechmatics users to discuss the product and for anyone wanting to learn more

Code for SDM'22-Cycle-Balanced Representation Learning For Counterfactual Inference

Converts an image into a set of triangles

Forecasting with LLMs

Harmony in Silence: A Speech-to-Text Empowerment Initiative for the Hard of Hearing Community.

Voice activity detector (VAD) for the browser with a simple API

Edge full-stack LLM platform. Written in Rust

simple streamlit chat app to talk with MistralAI's API.

A helpful Python package that helps you build excellent things inside Repls! 💻

Speech recognition module for Python, supporting several engines and APIs, online and offline.