snydersmarina's picture

snydersmarina

snydersmarina-37

AI & ML interests

None yet

Recent Activity

replied to shukdevdatta123's post about 4 hours ago

Introducing Kokoro TTS Translate For All users: https://huggingface.co/spaces/shukdevdatta123/Kokoro-TTS https://colab.research.google.com/drive/1DIpBzJSBBeTcpkyxkHcpngLumMapEWQz?usp=sharing (colab link for GPU access) Our Streamlit application provides a text-to-speech conversion tool using the Kokoro library, allowing users to input text, select language and voice, and adjust speech speed. The generated audio can be played or downloaded as a WAV file. Optionally, an OpenAI API key enables text translation to English, with subsequent speech generation for both the original and translated text. This functionality, along with helpful instructions and sample prompts, positions the application for various business opportunities. It can be offered as a SaaS platform with tiered subscriptions for access to features like diverse voices, languages, and translation. Target markets include content creators, language learning platforms, accessibility tools, and businesses needing automated voice responses. Further revenue streams can be generated through API integration with other applications, custom voice creation or cloning services, and affiliate marketing with related services.

replied to hexgrad's post about 4 hours ago

I wrote an article about G2P: https://hf.co/blog/hexgrad/g2p G2P is an underrated piece of small TTS models, like offensive linemen who do a bunch of work and get no credit. Instead of relying on explicit G2P, larger speech models implicitly learn this task by eating many thousands of hours of audio data. They often use a 500M+ parameter LLM at the front to predict latent audio tokens over a learned codebook, then decode these tokens into audio. Kokoro instead relies on G2P preprocessing, is 82M parameters, and thus needs less audio to learn. Because of this, we can cherrypick high fidelity audio for training data, and deliver solid speech for those voices. In turn, this excellent audio quality & lack of background noise helps explain why Kokoro is very competitive in single-voice TTS Arenas.

replied to MonsterMMORPG's post about 4 hours ago

VisoMaster (newest Open Source SOTA 0-shot Face Swap / Deep Fake APP) Tutorial and 1-Click Windows and Linux (Massed Compute) Installers 1-Click Installers > https://www.patreon.com/posts/121570322 For requirements follow this video : https://youtu.be/DrhUHnYfwC0 Follow below screenshots to learn how to use the APP Hopefully will make a tutorial video too VisoMaster VisoMaster is a powerful yet easy-to-use tool for face swapping and editing in images and videos. It utilizes AI to produce natural-looking results with minimal effort, making it ideal for both casual users and professionals. Features ✅ High-quality AI-powered face swapping for images and videos ✅ Easy-to-use interface with simple controls ✅ Supports multiple formats for input and output ✅ Efficient processing with GPU acceleration (CUDA support) ✅ Customizable models and fine-tuning options Official REPO : https://github.com/visomaster/VisoMaster You can also install via official repo Check below screenshots to learn how to use

View all activity

Organizations

None yet

models

None public yet

datasets

None public yet