Loading video...

Video Failed to Load

Go Home

📢 Introducing VERSA: our new open-source toolkit for speech & audio evaluation! - 80+ metrics in one unified interface - Flexible input support - Distributed evaluation with Slurm - ESPnet compatible Check out the details

shinjiw_at_cmu's profile picture

Shinji Watanabe

4,733 subscribers

10,154 views • 1 year ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

2 Comments

tamburaman's profile picture
tamburaman1 year ago

Great work!

Buttermilk's profile picture
Buttermilk1 year ago

So you also offer a leader board on speech recognition like open ASR?

Related Videos

📢Introducing Kaggle Game Arena: a new, open benchmark platform where top AI models compete in complex, strategic games in streamed match-ups. We're charting new frontiers for trustworthy AI evaluation and it begins with chess — a classic proving ground for system intelligence.
0:29

📢Introducing Kaggle Game Arena: a new, open benchmark platform where top AI models compete in complex, strategic games in streamed match-ups. We're charting new frontiers for trustworthy AI evaluation and it begins with chess — a classic proving ground for system intelligence.

Kaggle

114,176 views • 1 year ago

Introducing Gemini 3.1 Flash TTS 🗣️, our latest text to speech model with scene direction, speaker level specificity, audio tags, more natural + expressive voices, and support for 70 different languages. Available via our new audio playground in AI Studio and in the Gemini API!
0:33

Introducing Gemini 3.1 Flash TTS 🗣️, our latest text to speech model with scene direction, speaker level specificity, audio tags, more natural + expressive voices, and support for 70 different languages. Available via our new audio playground in AI Studio and in the Gemini API!

Logan Kilpatrick

805,885 views • 5 months ago

Today we’re celebrating 10 years of the Meta FAIR lab in Paris by sharing a collection of new models, datasets and some exciting milestones in the impacts of open source — all laddering up to our ongoing work to achieve Advanced Machine Intelligence (AMI). 1️⃣ Meta PARTNR is a framework for human-robot collaboration that builds on our existing work in this space with a new dataset and a large planning model enabling robots to accomplish complex tasks alongside humans. 2️⃣ Meta Audiobox Aesthetics enables the automatic evaluation of audio aesthetics, providing a comprehensive assessment of audio quality across speech, music and sound. 3️⃣ Open Source Machine Translation Benchmark is a carefully crafted collection with the aim of building an unprecedented multilingual machine translation benchmark for the community. 4️⃣ Two new breakthrough studies using AI to further our understanding of language in the brain.
2:28

Today we’re celebrating 10 years of the Meta FAIR lab in Paris by sharing a collection of new models, datasets and some exciting milestones in the impacts of open source — all laddering up to our ongoing work to achieve Advanced Machine Intelligence (AMI). 1️⃣ Meta PARTNR is a framework for human-robot collaboration that builds on our existing work in this space with a new dataset and a large planning model enabling robots to accomplish complex tasks alongside humans. 2️⃣ Meta Audiobox Aesthetics enables the automatic evaluation of audio aesthetics, providing a comprehensive assessment of audio quality across speech, music and sound. 3️⃣ Open Source Machine Translation Benchmark is a carefully crafted collection with the aim of building an unprecedented multilingual machine translation benchmark for the community. 4️⃣ Two new breakthrough studies using AI to further our understanding of language in the brain.

AI at Meta

86,004 views • 1 year ago

Introducing Indic Parler-TTS: Open-Source Text-to-Speech for Over a Billion Indic Speakers! 🌏 In collaboration with Hugging Face, we are excited to release Indic Parler-TTS, a state-of-the-art open-source text-to-speech system designed to bring accessible and high-quality speech technology to India’s diverse linguistic community. Supporting 20 of the 22 scheduled Indian languages—and English in various accents (US, British, Indian)—it’s built to serve over a billion speakers and empower companies, developers, researchers, and communities. Why Indic Parler-TTS Stands Out: 1. Open and Accessible: Fully open-source with permissive licensing for unrestricted usage. 2. Wide Language Support: Includes a vast range of Indic languages, with rich diversity in voices. 3. High-Quality Audio: Produces natural, clear, and lifelike speech. 4. Adaptable and Fine-Tunable: Customize it to new languages, accents, or specific applications. 5. State-of-the-Art Performance: Proven through rigorous evaluation. 6. Versatile and Inclusive: Indic Parler-TTS offers 69 unique voices across 18 Indian languages, making it a perfect fit for diverse use cases like audiobooks, virtual assistants, and educational tools. Let's democratize speech technology together and make speech technology more inclusive and accessible for everyone. ▶️ Experience it now: Demo: Model page:
1:06

Introducing Indic Parler-TTS: Open-Source Text-to-Speech for Over a Billion Indic Speakers! 🌏 In collaboration with Hugging Face, we are excited to release Indic Parler-TTS, a state-of-the-art open-source text-to-speech system designed to bring accessible and high-quality speech technology to India’s diverse linguistic community. Supporting 20 of the 22 scheduled Indian languages—and English in various accents (US, British, Indian)—it’s built to serve over a billion speakers and empower companies, developers, researchers, and communities. Why Indic Parler-TTS Stands Out: 1. Open and Accessible: Fully open-source with permissive licensing for unrestricted usage. 2. Wide Language Support: Includes a vast range of Indic languages, with rich diversity in voices. 3. High-Quality Audio: Produces natural, clear, and lifelike speech. 4. Adaptable and Fine-Tunable: Customize it to new languages, accents, or specific applications. 5. State-of-the-Art Performance: Proven through rigorous evaluation. 6. Versatile and Inclusive: Indic Parler-TTS offers 69 unique voices across 18 Indian languages, making it a perfect fit for diverse use cases like audiobooks, virtual assistants, and educational tools. Let's democratize speech technology together and make speech technology more inclusive and accessible for everyone. ▶️ Experience it now: Demo: Model page:

AI4Bharat

28,681 views • 1 year ago

👉 New | 📢 Introducing… EMBRConnect 📢 Connect with EMBRC in our new marine innovation newsletter to get: ➡️ EMBRC’s news ➡️ Marine science developments ➡️ New papers ➡️ Calls for proposals ➡️ Funding opps ➡️ Webinars & events ➡️ Glimpses behind-the-scenes Don’t miss out
0:38

👉 New | 📢 Introducing… EMBRConnect 📢 Connect with EMBRC in our new marine innovation newsletter to get: ➡️ EMBRC’s news ➡️ Marine science developments ➡️ New papers ➡️ Calls for proposals ➡️ Funding opps ➡️ Webinars & events ➡️ Glimpses behind-the-scenes Don’t miss out

EMBRC (European Marine Biological Resource Centre)

203,257 views • 1 year ago

New content will arrive in #ForzaMotorsport every month introducing new challenges for you and your friends to enjoy! Here’s Chris Esaki with the details and for a full breakdown of the cars and events coming in October, check out the Forza blog:
0:21

New content will arrive in #ForzaMotorsport every month introducing new challenges for you and your friends to enjoy! Here’s Chris Esaki with the details and for a full breakdown of the cars and events coming in October, check out the Forza blog:

Forza Motorsport

141,607 views • 3 years ago

📢 Announcing one of the most exciting works from us this year on **scalable robot policy evaluation through real-to-sim transfer**, moving toward a scalable evaluation engine with structured world models that capture the appearance, geometry, and dynamics of environments involving deformable objects. 🤖 Evaluation remains one of the biggest bottlenecks in building general-purpose robots. Today, robots are still evaluated only in the real world, which is **orders of magnitude slower** than the development of language agents. We propose a new framework where simulation performance **strongly correlates** with the real world (r > 0.9), even for deformable objects. The key difference from existing work lies in the correlation between simulation and reality: if a robot model performs better in the digital world, does it also perform better in the real world? This question has long made people hesitant about simulation-based evaluation — especially for deformable objects. We are changing that. Our pipeline achieves effective real-to-sim transfer, establishing **state-of-the-art correlation** between simulation and reality for deformable object manipulation. It provides a **scalable and reproducible evaluation engine** for robot learning. 🌐
3:04

📢 Announcing one of the most exciting works from us this year on **scalable robot policy evaluation through real-to-sim transfer**, moving toward a scalable evaluation engine with structured world models that capture the appearance, geometry, and dynamics of environments involving deformable objects. 🤖 Evaluation remains one of the biggest bottlenecks in building general-purpose robots. Today, robots are still evaluated only in the real world, which is **orders of magnitude slower** than the development of language agents. We propose a new framework where simulation performance **strongly correlates** with the real world (r > 0.9), even for deformable objects. The key difference from existing work lies in the correlation between simulation and reality: if a robot model performs better in the digital world, does it also perform better in the real world? This question has long made people hesitant about simulation-based evaluation — especially for deformable objects. We are changing that. Our pipeline achieves effective real-to-sim transfer, establishing **state-of-the-art correlation** between simulation and reality for deformable object manipulation. It provides a **scalable and reproducible evaluation engine** for robot learning. 🌐

Yunzhu Li

39,960 views • 11 months ago

Realtime interactive generative models FTW! Announcing a new 🌊 of details and features for Magenta RealTime, the open weights live music AI model from GDM! * Live Jamming with audio input 🎤🎸🎵 * Personalize your own models 🔧 * Tech report 📜 Links below in the 🧵...
1:31

Realtime interactive generative models FTW! Announcing a new 🌊 of details and features for Magenta RealTime, the open weights live music AI model from GDM! * Live Jamming with audio input 🎤🎸🎵 * Personalize your own models 🔧 * Tech report 📜 Links below in the 🧵...

Jesse Engel

183,794 views • 1 year ago

Introducing FLUX 3. One multi-modal model for Image, Video, Audio and Action-Prediction. Creations are truer to life in every kind of style. FLUX 3 Video is now available in early access (link below). Jointly trained in one unified architecture, our model can be extended to predict actions for robotics. See our work with mimic and Audi in the thread.
0:46

Introducing FLUX 3. One multi-modal model for Image, Video, Audio and Action-Prediction. Creations are truer to life in every kind of style. FLUX 3 Video is now available in early access (link below). Jointly trained in one unified architecture, our model can be extended to predict actions for robotics. See our work with mimic and Audi in the thread.

Black Forest Labs

1,217,057 views • 2 months ago

Introducing Morph Studio, an all-in one AI video workflow. Ignite your creativity with our story playground 🧩 Releasing access to waitlisted users starting today. Join the waitlist here: Find out more details about new features in the thread🧵 below!
0:55

Introducing Morph Studio, an all-in one AI video workflow. Ignite your creativity with our story playground 🧩 Releasing access to waitlisted users starting today. Join the waitlist here: Find out more details about new features in the thread🧵 below!

Morph Studio

54,443 views • 2 years ago

📢 GCSEs in Wales are changing! Today, we’ve published details of the new Made-for-Wales #GCSEs coming to Wales from 2025, to align with the Curriculum for Wales. Find out what’s changing and when in our decisions reports ⬇️
0:45

📢 GCSEs in Wales are changing! Today, we’ve published details of the new Made-for-Wales #GCSEs coming to Wales from 2025, to align with the Curriculum for Wales. Find out what’s changing and when in our decisions reports ⬇️

Qualifications Wales

22,445 views • 3 years ago

Introducing Theoriq’s AlphaSwarm! ⚡️ We’re thrilled to give developers access to a starter toolkit for building AI-powered trading agents in DeFi (AiFi)! 🦾 AlphaSwarm streamlines agent and swarm development, making it easier to build, execute, and refine collaborative agents that can analyze real-time market signals, and autonomously execute trades across multiple chains. Check out our latest blog for more details! 👇 You can explore the toolkit directly in Theoriq’s GitHub: Or if you’re a developer interested in building the future of AiFi, join our dev community in Discord:
0:30

Introducing Theoriq’s AlphaSwarm! ⚡️ We’re thrilled to give developers access to a starter toolkit for building AI-powered trading agents in DeFi (AiFi)! 🦾 AlphaSwarm streamlines agent and swarm development, making it easier to build, execute, and refine collaborative agents that can analyze real-time market signals, and autonomously execute trades across multiple chains. Check out our latest blog for more details! 👇 You can explore the toolkit directly in Theoriq’s GitHub: Or if you’re a developer interested in building the future of AiFi, join our dev community in Discord:

Theoriq

103,962 views • 1 year ago

Summer Campfire laid out our progress and focus for Mobile and the Official Client, including: ↕️ Menu Entry Swapper Fixes 🏷️ Bank Tags 📲 Android Picture in Picture 🛠️ New Renderer Open Beta 2 Check out the blog for the details and make sure to fill out the survey.
0:58

Summer Campfire laid out our progress and focus for Mobile and the Official Client, including: ↕️ Menu Entry Swapper Fixes 🏷️ Bank Tags 📲 Android Picture in Picture 🛠️ New Renderer Open Beta 2 Check out the blog for the details and make sure to fill out the survey.

Old School RuneScape

24,375 views • 4 months ago

A lot of wonderful people asking how they can support the Foundation. One great way is by joining Doddie Aid - our mass-participation exercise challenge 💪 Check out the promo video for more details & download the app/ tap the link below to take part 👇
0:46

A lot of wonderful people asking how they can support the Foundation. One great way is by joining Doddie Aid - our mass-participation exercise challenge 💪 Check out the promo video for more details & download the app/ tap the link below to take part 👇

My Name'5 Doddie Foundation

40,887 views • 3 years ago

Introducing OpenBooth A portable Physical AI lab with upgraded SO-101 arms. Calibrate, train, and share your robot skills, all from MakerMods Lab. 150+ open source datasets. Hackathon-winner policies. Built along with Isaac Sin and our team at MakerMods Robotics Check it out in the link down below:
0:46

Introducing OpenBooth A portable Physical AI lab with upgraded SO-101 arms. Calibrate, train, and share your robot skills, all from MakerMods Lab. 150+ open source datasets. Hackathon-winner policies. Built along with Isaac Sin and our team at MakerMods Robotics Check it out in the link down below:

Ryan Chan

21,424 views • 1 month ago

Check this out!🔥 Modified version of TripoSR (open source 2D to 3D tool). This version outputs USDZ directly for Apple Vision Pro.🥽 You can easily create 3D objects in AVP with one click & view them in your space! Modified repo in the thread 🧵👇
0:30

Check this out!🔥 Modified version of TripoSR (open source 2D to 3D tool). This version outputs USDZ directly for Apple Vision Pro.🥽 You can easily create 3D objects in AVP with one click & view them in your space! Modified repo in the thread 🧵👇

Blaine Brown

48,111 views • 2 years ago