An Optimized Speech-to-Text Pipeline for the Whisper Model.
Directory
Search results
Published directory entries matching your search.
Enterprise-grade Voice AI simulation SDK for scenario-driven stress testing of multimodal and agentic systems.
Generate TikTok Text-to-Speech voices in your browser
Simple Python script to interact with the TikTok TTS API
Accelerates transcription with the combination of OpenAI's Whisper Large v2, HF Transformers, Optimum, and flash attention.
An offline speech recognition toolkit with C++ support, designed for low-resource devices and multiple languages.
A simple and efficient end-to-end Automatic Speech Recognition (ASR) system from Facebook AI Research.
A Whisper CLI client compatible with the original OpenAI client, using CTranslate2 for faster inference. opensource.
Port of OpenAI's Whisper model in C/C++. opensource.
↗ external - Open-source dictation that types where you talk.
Aesthetic Wallpapers helps customize desktop wallpapers, themes, backgrounds, or visual system appearance.
Self-improving agents that learn from execution feedback. LangChain integration for agents that curate their own context.
) - Amber is a nostr event signer for Android. It allows users to keep their nsec segregated in a single, dedicated app. The goal of Amber is to have your smartphone act as a NIP-46 signing device without any need for servers or additional hardware. "Private keys should be exposed to as few systems as possible as each system adds to the attack surface," as the rationale of said NIP states. In addition to native apps,
ඞ Among-us themed OS.
) - Anonostr allows users to send anonymous notes to the Nostr network without revealing their identity. For each note submission, the app generates a new key pair, sends the note through select relays, and then securely burns the key pair. It supports tagging, threading, quoting, and replying to existing notes.
Awesome Web Desktops helps customize desktop wallpapers, themes, backgrounds, or visual system appearance.
Bazzite makes gaming and everyday use smoother and simpler across desktop PCs, handhelds, tablets, and home theater PCs.
A series of plugins and themes for BetterDiscord.
) - An efficient, scalable, and deduplicated local blob storage that maintains metadata in SQLite. Fully compatible with Blossom, it gives developers a reliable database option for building their own Blossom servers.
Latest Papers and Datasets on Multimodal Large Language Models, and Their Evaluation.
Theano based library for deep and recurrent neural networks.
) - Workspace where AI agents and humans collaborate on their own relay.
An open-source SDK package for Flutter that provides developers with seamless integration and access to Snapchat's CameraKit features within their Flutter applications.
Curated list of classless CSS themes and frameworks for styling semantic HTML quickly.