#
Lists (1)
Starred repositories
Vision-first AI agent for desktop automation. Fully offline. Powered by YOLO, OCR & ResNet β building towards local intelligence.
This repository contains information about Cloud GPU offerings for Machine Learning practitioners.
Session Android - A Decentralized, Onion Routed, Private Messenger
Provide a vocabulary-based algorithm for measuring the clustering of software systems with disconnected call graphs
πΉ Hackable charting lib for traders. You can draw literally ANYTHING on top of candlestick charts. [Not Maintained]
β‘ The largest subscription that have vless / vmess / trojan / shadowsocks configs
a lightweight cms self-hosted on cloudflare, for podcasts, blogs, photos, videos, documents, and curated urls.
ππ¬ Code along Duolingo clone with Antonio and a Twist! π₯π§π½ββοΈ
unofficial vits2-TTS implementation in pytorch
Dolphin is a multilingual, multitask ASR model jointly trained by DataoceanAI and Tsinghua University.
YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open
PyTorch code implementation of EfficientSpeech - to be presented at ICASSP2023.
AI-Powered Podcast Generator: A Python-based tool that converts text scripts into realistic audio podcasts using Google's Generative AI API. This project leverages advanced text-to-speech technologβ¦
This repository hosts BonyadAI, a Persian question answering AI Model. We developed an initial web crawler and scraper to gather the dataset. The second phase involved building a machine learning mβ¦
Fine-tuning & Reinforcement Learning for LLMs. π¦₯ Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
A high-performance, zero-overhead, extensible Python compiler with built-in NumPy support
StreamSpeech is an βAll in Oneβ seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.
Hibiki is a model for streaming speech translation (also known as simultaneous translation). Unlike offline translationβwhere one waits for the end of the source utterance to start translating--- Hβ¦
convert subtitle (.srt) to speech (.wav) using google API
A list of SaaS, PaaS and IaaS offerings that have free tiers of interest to devops and infradev
Persian text-to-speech streamlit interface
NLP-persian-poet-identification
Easily train a good VC model with voice data <= 10 mins!
Text Dataset for Pashto Language
MARY TTS -- an open-source, multilingual text-to-speech synthesis system written in pure java
The data plane for agents. Arch is a models-native proxy server that handles the plumbing work in AI: agent routing & hand off, guardrails, zero-code logs and traces, unified access to LLMs from Opβ¦