3arab TTS 500M v2 VoiceDesign

--- license: apache-2.0 language: - ar base_model: - sherif1313/3arab-TTS-500M-v2 pipeline_tag: text-to-speech --- <p align="center"> <img src="pic.jpg" width="400"/> <p> <p align="center"> 💜 <a href="https://github.com/sherif1313/3arab-TTS/"><b>Github</b></a>&nbsp&nbsp | &nbsp&nbsp🤗 <a href="https://huggingface.co/sherif1313/">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp📚 <a href="https://github.com/sherif1313/Arabic-English-handwritten-OCR-v3/tree/main">Cookbooks</a>&nbsp&nbsp <br> 🖥️ <a href="https://huggingface.co/spaces/sherif1313/3arab-TTS-VoiceDesign-v2">Demo</a>&nbsp&nbsp </a> </p> ## 🌍 3arab-TTS An independent Arabic Text-to-Speech (TTS) model based on the **Rectified Flow Diffusion Transformer (RF-DiT)** architecture.with Voice Design capabilities for controllable speaker identity, pitch, and style.Instead of requiring reference audio for voice cloning, this model features Voice Design 70 different voices The acoustic model was trained entirely from scratch on Arabic speech data using random initialization, with independently developed training and inference pipelines. ## Voice Design Unlike traditional Arabic TTS systems that require reference audio, the model can generate different speaker styles directly from natural-language voice descriptions without providing a reference recording. ## ⚠️ What's New ## Current Version: v2 - ~553M parameters - ~700 hours of Arabic speech - 48 kHz audio generation - DACVAE latent codec - RF-DiT acoustic model Due to the limited availability of large-scale open Arabic speech datasets, a significant portion of the training data was collected from publicly available Arabic content and carefully filtered for quality. The current release include integrated audio watermarking. SilentCipher watermarking inference releases without affecting audio quality. ## The current release demonstrates that open-source Arabic TTS systems can achieve a level of quality and naturalness comparable to many production-grade solutions. With over 700 hours of carefully curated Arabic speech and a large-scale RF-DiT architecture, 3arab-TTS establishes a strong baseline for next-generation Arabic speech synthesis. ## Future versions will focus on: improving expressive speech generation ## 🤝 Community Contributions Welcome Contributions are highly appreciated, including: Arabic speech datasets training improvement...

Source context: 0 downloads · 2 likes · Pipeline text-to-speech · Repo sherif1313/3arab-TTS-500M-v2-VoiceDesign