Stars
Unofficial WIP LoRa Finetuning repository for VibeVoice
Demo repository for Kyutai Labs' STT-1B model: Real-time speech-to-text transcription with streaming inference, built-in VAD, and Jupyter notebook examples for audio processing and simulation.
Unsloth Studio is a web UI for training and running open models like Qwen, DeepSeek, gpt-oss and Gemma locally.
Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audi…
In this Repo, you can easily fine-tune different variations of the Whisper model to your specific multilingual data based on a simple manifest.
An application to make phone calls and connect to a AI assistant who will answer your questions in realtime
Build AI WhatsApp Bots with Pure Python
This is a demonstration on how to produce speech in a particular emotion from text, this is achieved by fine tuning a TTS model on emotion labelled speech data, formulating it as a multi-modal prob…
Fine-tuning Vietnamese Text-to-speech model (VITS)
Build local voice agents with open-source models
A collection of notebooks/recipes showcasing usecases of open-source models with Together AI.
jupyter notebooks to fine tune whisper models on Vietnamese using Colab and/or Kaggle and/or AWS EC2
An open-source alternative to OpenAI and Gemini's deep research.
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Beginner Level Deep Learning Tutorials in Pytorch with Youtube Videos!
An extremely fast Python package and project manager, written in Rust.
Notebooks for the Practicals at the Deep Learning Indaba 2024.
Audio Transcription WhatsApp Bot using Whisper
This script checks airtable table and if there is a new row added to table adds the content to a pdf and mails it.
python flask app serving as webhook for whatsapp business accounts making prompts to openai api
🧠💬 Articles I wrote about machine learning, archived from MachineCurve.com.
This repository is deprecated and will be archived