Loading video...

Video Failed to Load

Go Home

New side project: Samuel, a model I trained to mimic speech using Pink Trombone, a (pre-existing) silly vocal tract simulator. 🧵

vvolhejn's profile picture

Václav Volhejn

1,181 subscribers

143,822 views • 2 days ago •via X (Twitter)

ArtsScience & TechnologyEducation
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

🏗️ Policy Adaptation from Foundation Model Feedback #CVPR2023 Instead of using foundation model as a pre-trained encoder (generator), we use it as a Teacher (discriminator) to tell where our policy did wrong and helps it adapts to new envs and tasks.
1:53

🏗️ Policy Adaptation from Foundation Model Feedback #CVPR2023 Instead of using foundation model as a pre-trained encoder (generator), we use it as a Teacher (discriminator) to tell where our policy did wrong and helps it adapts to new envs and tasks.

Xiaolong Wang

24,412 views • 3 years ago

Announcing Talkie: a new, open-weight historical LLM! We trained and finetuned a 13B model on a newly-curated dataset of only pre-1930 data. Try it below! with Alec Radford and Nick Levine 🧵
7:58

Announcing Talkie: a new, open-weight historical LLM! We trained and finetuned a 13B model on a newly-curated dataset of only pre-1930 data. Try it below! with Alec Radford and Nick Levine 🧵

David Duvenaud

1,462,772 views • 3 months ago

Wanna start dev Starknet projects ? Made a quick tool using kickstart, a Rust CLI to easily get a new project up and running by using pre-made templates. It will create a ready to use project using the great Starknet Foundry toolchain.
1:00

Wanna start dev Starknet projects ? Made a quick tool using kickstart, a Rust CLI to easily get a new project up and running by using pre-made templates. It will create a ready to use project using the great Starknet Foundry toolchain.

abdel

13,906 views • 3 years ago

Gemini 3.1 Flash TTS is our most controllable text-to-speech model yet. With new Audio Tags, you can easily direct vocal style, delivery, and pace through text commands. 🧵
0:33

Gemini 3.1 Flash TTS is our most controllable text-to-speech model yet. With new Audio Tags, you can easily direct vocal style, delivery, and pace through text commands. 🧵

Google DeepMind

470,406 views • 4 months ago

MVDiffusion: How to take a pre-trained text2image model for a perspective view (e.g., Stable Diffusion) and retrain to generate multiple consistent views (e.g., a panorama). Project site: Hugging Face demo: Code out in a month.
0:23

MVDiffusion: How to take a pre-trained text2image model for a perspective view (e.g., Stable Diffusion) and retrain to generate multiple consistent views (e.g., a panorama). Project site: Hugging Face demo: Code out in a month.

Yasutaka Furukawa

33,456 views • 3 years ago

Trump reportedly has a speech prewritten to address aliens existing so now might be a good time to review Project Blue Beam
2:49

Trump reportedly has a speech prewritten to address aliens existing so now might be a good time to review Project Blue Beam

Shipwreck

34,765 views • 6 months ago

The new open-source Text to Speech model: Fish Speech 1.4 is brilliant! Trained on a massive 700K hours of multilingual speech data in 8 languages - Instant voice cloning 🗣️ - Ultra-low latency ⚡ - Compact model (~1GB weights) 🏋️‍♂️
1:23

The new open-source Text to Speech model: Fish Speech 1.4 is brilliant! Trained on a massive 700K hours of multilingual speech data in 8 languages - Instant voice cloning 🗣️ - Ultra-low latency ⚡ - Compact model (~1GB weights) 🏋️‍♂️

Rohan Paul

228,890 views • 1 year ago

I trained a neural network to mimic a forest trail near my apartment (web demo in the post)
1:43

I trained a neural network to mimic a forest trail near my apartment (web demo in the post)

Ollin Boer Bohan

118,477 views • 1 year ago

I got Apple's visionOS Simulator streaming wirelessly to a Meta Quest using ALVR. Download: Demo of using the visionOS Simulator inside VR:
2:08

I got Apple's visionOS Simulator streaming wirelessly to a Meta Quest using ALVR. Download: Demo of using the visionOS Simulator inside VR:

Zhuowei Zhang

150,025 views • 3 years ago

Today mimic and friends are excited to share mimic-video, a new class of Video-Action Model that elevates video model backbones as first class citizens for robot learning!
2:07

Today mimic and friends are excited to share mimic-video, a new class of Video-Action Model that elevates video model backbones as first class citizens for robot learning!

Elvis Nava

88,368 views • 8 months ago

Using our brain simulator, we’ve trained a reinforcement learning agent to maximize bits per second. Here is the RL policy converting brain data to cursor control in simulation:
0:29

Using our brain simulator, we’ve trained a reinforcement learning agent to maximize bits per second. Here is the RL policy converting brain data to cursor control in simulation:

Neuralink

18,410 views • 1 year ago

After doing wuwa story when I finally had a free time, I ended liking Carlotta a lot. So I get myself a modified Carlotta model. Here is a test to it using my existing motion. #ryona #リョナ #mmd
0:35

Sensitive content

After doing wuwa story when I finally had a free time, I ended liking Carlotta a lot. So I get myself a modified Carlotta model. Here is a test to it using my existing motion. #ryona #リョナ #mmd

Stelle Jades

49,863 views • 1 year ago

introducing: "bwam" AI Deployer A new AI model, trained only on coins deployed by the infamous "bwam" deployer wallet. Deploy coins like a professional using uDev.
0:31

introducing: "bwam" AI Deployer A new AI model, trained only on coins deployed by the infamous "bwam" deployer wallet. Deploy coins like a professional using uDev.

uxento

80,856 views • 3 months ago

Introducing EpsteinVR: A full 3D model of Jeffrey's Upper East Side mansion (and more), generated using Apple's new SHARP Gaussian Splat model. Coming soon to Jmail Suite at jmail . world
2:42

Introducing EpsteinVR: A full 3D model of Jeffrey's Upper East Side mansion (and more), generated using Apple's new SHARP Gaussian Splat model. Coming soon to Jmail Suite at jmail . world

Diego Rodriguez

2,326,998 views • 8 months ago

Check out our #ICRA2025 paper where we train a robotic puppy to dance expressively! Our method, Deep Fourier Mimic, a generalized version of DeepMimic, enables automatic parameterization of reference data. Project site: Video: 🧵
1:11

Check out our #ICRA2025 paper where we train a robotic puppy to dance expressively! Our method, Deep Fourier Mimic, a generalized version of DeepMimic, enables automatic parameterization of reference data. Project site: Video: 🧵

Robotic Systems Lab

60,728 views • 1 year ago

OpenAI just released a new model to distinguish between AI/human written text to protect against ChatGPT. The classifier was trained on a pair of AI/human written dataset. However.. I was easily able to trick it by using GPT3 to rewrite the text. Demo:
0:32

OpenAI just released a new model to distinguish between AI/human written text to protect against ChatGPT. The classifier was trained on a pair of AI/human written dataset. However.. I was easily able to trick it by using GPT3 to rewrite the text. Demo:

Lior Alexander

195,429 views • 3 years ago

Yesterday we introduced SeamlessExpressive — a new model that preserves unique vocal styles & expression for speech translation, built on our SeamlessM4T v2 foundation model. More details on the family of Seamless Communication models ➡️
2:36

Yesterday we introduced SeamlessExpressive — a new model that preserves unique vocal styles & expression for speech translation, built on our SeamlessM4T v2 foundation model. More details on the family of Seamless Communication models ➡️

AI at Meta

189,972 views • 2 years ago

Working on a long-weekend side project with v0. Inspired by this week’s SpaceX launch, I built a simulator that respects some real physics, then added a few things to make it a little more fun. Hopefully I’ll be able to share a playable version soon.
0:50

Working on a long-weekend side project with v0. Inspired by this week’s SpaceX launch, I built a simulator that respects some real physics, then added a few things to make it a little more fun. Hopefully I’ll be able to share a playable version soon.

Evil Rabbit

57,153 views • 2 months ago

Devs are using Memory Bank as a project architecture and planning tool before they write any code. "I prefer starting in Cline, using Memory Bank to build out the context files as a roadmap, and letting Cline take the wheel." How to use Memory Bank for project planning 🧵
1:16

Devs are using Memory Bank as a project architecture and planning tool before they write any code. "I prefer starting in Cline, using Memory Bank to build out the context files as a roadmap, and letting Cline take the wheel." How to use Memory Bank for project planning 🧵

Cline

96,628 views • 1 year ago