Activity
Stars and mentions · Last 30 days, Oct 5 – Nov 3
Top repositories
KittenML’s repositories ranked by new stars, as on trending.
Contributes to
Repositories outside KittenML’s account where KittenML opened or reviewed pull requests in the past 365 days.
Who noticed KittenML
Everyone who starred or forked KittenML’s repositories since the archive began in 2011.
Notable accounts
Ordered by the stars their own repositories have received.
Biggest fans
Accounts that starred the most of these repositories.
Breakout weeks
Each repository’s best week of new stars, with the release published around it.
Achievements
Awards earned by the repositories KittenML owns. Select an award to embed its badge.
- Gold
- 01st place finishes
- Silver
- 32nd place finishes
- Bronze
- 13rd place finishes
- Awarded repositories
- 1Owned by KittenML now
Repositories
Ordered by gold, then silver, then bronze.
- KittenTTSBest: 2nd by stars, 1,263 stars031
A repository earns an award for finishing first, second or third in a completed trending day or week, ranked by new stars, new forks or pull request authors. Awards follow a repository through renames and transfers and count toward its current owner. Weeks run Monday to Sunday, UTC.
Mentions
حجمه فقط 25 م.ب نموذج ذكاء إصطناعي خفيف مهمته تحويل النص إلى صوت ويدعم اللغة العربية كلغة مدعومة من ضمن 20 لغة في النموذج سيفيد من يريد دمجه مع تطبيق هاتف ذكي أو برنامج كمبيوتر ويحتاج مكتبات خفيفة الحجم رابط المشروع: KittenML/KittenTTS #تقنية #ذكاء_اصطناعي t.co
@fmontes @ElevenLabs Y no, podrias clonarla Creo que este repo te podría servir KittenML/KittenTTS
You want voice cloning without fine-tuning. KittenTTS gives you that from a short clip. With more than 10,000 stars on GitHub, it's a popular open-source text-to-speech library with two model families behind one constructor. KittenML/KittenTTS t.co
1.7Bの音声AIがGPUなしでリアルタイム動作。 KittenTTS 2は1.58bitの3値重みで軽量化。日本語にも対応し、5〜30秒の音声から声のクローンまで可能。感情表現も制御できる。 ローカル音声AIの進化がすごい。ただし重みは独自ライセンスなので注意。 GitHub KittenML/KittenTTS
Kitten-TTS 2: New Open-source SOTA 1.58 bit TTS (CPU-only with voice cloning, multilingual, emotion control) KittenML has just released code and weights of Kitten-TTS 2, which is a super-efficient frontier TTS model, and the world's first 1.58-bit TTS model. It runs in real time on just a CPU, with zero-shot voice cloning, multilingual support, and expressive / emphasis control. Code and weights are open-source. Ternary(1.58-bit) Weights means it can run locally or be self-hosted for super-cheap. Github: KittenML/KittenTTS Hugging Face: huggingface.co KittenML's Discord: discord.com Key features and Advantages 1. Ternary TTS: Every linear weight in the body is one of three values (-1, 0, +1) with group size of 128 for scales. Tiny footprint and fast CPU inference. The model has 1.7B parameters. 2. Real-time on CPU and consumer GPU's too: No GPU needed for real-time generation. Optimized ternary kernels for CPU inference provided. 3. Expressive voice cloning: zero-shot cloning from less than 5 seconds of reference audio, and it keeps the expressivity, accent information etc. No fine-tuning needed. 4. Multilingual TTS: Model supports voice cloning in 20+ languages. Cross-language voice cloning can be used to create accented speech too. 5. Expressive / emphasis control: you can steer the delivery and stress specific words, not just pick a voice. Details in the Readme. 6. Open source (hell yeah!): code and weights are open-source and free to use. It's an oss alternative to elevenlabs for gpu-poor folks. easy to self-deploy or run locally. 7. What changed from V0.8 to 2: higher quality. Completely new architecture, natural sounding speech, ternary weights, zero-shot voice cloning, multilingual, and emphasis/emotion control.
15M parameters and under 25MB? That’s impressive. 🔥 Small, expressive TTS models like this could make local AI voice generation much more accessible to developers. @divamgupta KittenML/KittenTTS