Загрузка видео...

Не удалось загрузить видео

На главную

Trained another voice lora using VOXCPM. Also got the TTS running near real time with a Rust port and WSL Absolutely incredible. This one was trained on 20 clips. Not releasing these for obvious reasons - purely for science

AIWarper's profile picture

A.I.Warper

36,275 subscribers

28,531 просмотров • 3 месяцев назад •via X (Twitter)

ИгрыЗдоровье и велнесНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Another example of the multiple TTS parallel pipelines pattern. Here's a voice AI agent that speaks both English and Arabic, using a specific model/voice for each language. These are PlayAI voices. The STT, TTS, and LLM inference is all running on Groq Inc. (The LLM is LLama 4 Maverick.)
1:26

Another example of the multiple TTS parallel pipelines pattern. Here's a voice AI agent that speaks both English and Arabic, using a specific model/voice for each language. These are PlayAI voices. The STT, TTS, and LLM inference is all running on Groq Inc. (The LLM is LLama 4 Maverick.)

kwindla

13,401 просмотров • 1 год назад

NEW: Higgs Audio V2 from BosonAI open, unified TTS model w/ voice cloning, beats GPT 4o mini tts and ElevenLabs v2 🔥 > Trained on 10M hours (speech, music, events) > Built on top of Llama 3.2 3B > Works real-time and on edge > Beats GPT-4o-mini-tts, ElevenLabs v2 in prosody & emotion Multi-speaker dialog > Zero-shot voice cloning 🤩 > Available on Hugging Face Kudos to folks at Boson AI for releasing such a brilliant work and all the details around the model! 🤗
2:10

NEW: Higgs Audio V2 from BosonAI open, unified TTS model w/ voice cloning, beats GPT 4o mini tts and ElevenLabs v2 🔥 > Trained on 10M hours (speech, music, events) > Built on top of Llama 3.2 3B > Works real-time and on edge > Beats GPT-4o-mini-tts, ElevenLabs v2 in prosody & emotion Multi-speaker dialog > Zero-shot voice cloning 🤩 > Available on Hugging Face Kudos to folks at Boson AI for releasing such a brilliant work and all the details around the model! 🤗

Vaibhav (VB) Srivastav

79,585 просмотров • 1 год назад

I tested Rust vs Javascript for games 🎮 I had this question recently and decided to port my Three.js game to Rust Desktop I'm still not able to reproduce the same look on both games but I believe that codewise they are very similar With both games running, the Rust version averages 37FPS while the Three.js version averages around 20FPS If I'm running one game at a time the FPS goes up considerably (60 FPS on both with power on) So the Rust version for Desktop has 85% increase in performance on my Macbook Pro M4 This comparision is basically comparing Browser vs Native, which is not completely fair So that's why I want to port the Rust version to WASM on the browser and benchmark again soon
0:44

I tested Rust vs Javascript for games 🎮 I had this question recently and decided to port my Three.js game to Rust Desktop I'm still not able to reproduce the same look on both games but I believe that codewise they are very similar With both games running, the Rust version averages 37FPS while the Three.js version averages around 20FPS If I'm running one game at a time the FPS goes up considerably (60 FPS on both with power on) So the Rust version for Desktop has 85% increase in performance on my Macbook Pro M4 This comparision is basically comparing Browser vs Native, which is not completely fair So that's why I want to port the Rust version to WASM on the browser and benchmark again soon

André → andreelias.dev

92,815 просмотров • 2 месяцев назад

Here is a real-life run, end-to-end from training to using the trained LLM in LM Studio by LM Studio MLX-LoRA-Studio gives you a user friendly, extremely customisable training interface for fine-tuning and training LLMs. Its a MacOS native app, front- and backend. Will be releasing the App in the coming days. GH Repo:
4:41

Here is a real-life run, end-to-end from training to using the trained LLM in LM Studio by LM Studio MLX-LoRA-Studio gives you a user friendly, extremely customisable training interface for fine-tuning and training LLMs. Its a MacOS native app, front- and backend. Will be releasing the App in the coming days. GH Repo:

Gökdeniz Gülmez

11,906 просмотров • 1 месяц назад

Building real-time voice AI just got a lot easier 🤖✨ Introducing our new Python AI SDK for building real-time AI integrations directly into Stream Video. With out-of-the-box integrations with , Deepgram, , OpenAI, Moonshine AI, and more, developers can mix and match between real-time Voice AI, TTS or STT models. Get started 👇
0:49

Building real-time voice AI just got a lot easier 🤖✨ Introducing our new Python AI SDK for building real-time AI integrations directly into Stream Video. With out-of-the-box integrations with , Deepgram, , OpenAI, Moonshine AI, and more, developers can mix and match between real-time Voice AI, TTS or STT models. Get started 👇

Stream

224,782 просмотров • 1 год назад

24 hours. No Sleep. Constant Running. 11 million dollars. Would you keep running??? French Artist, Rilés accepted a challenge to run nonstop for 24hrs with $11m on the line. He trained for two years and pulled this off
0:40

24 hours. No Sleep. Constant Running. 11 million dollars. Would you keep running??? French Artist, Rilés accepted a challenge to run nonstop for 24hrs with $11m on the line. He trained for two years and pulled this off

Dr. God Abeg ooo

4,647,082 просмотров • 7 месяцев назад

🚀 VoxCPM 2 is live! 🎉 Another open-source AI #TTS model from China — and one that stands shoulder to shoulder with Qwen3-TTS, while bringing everything into a single unified model. After rapid iterations from V1 (zero-shot cloning) to V1.5 (long-form + fine-tuning), #VoxCPM has consistently pushed quality and usability forward. Now, VoxCPM 2 takes it further: 🔹30+ languages — truly global, truly local. 🔹Infinite voice design — type it, hear it, control it. From a whisper to a booming cinematic voice. 🔹Studio-grade audio — 48kHz ultra-high fidelity with emotional depth 🔹Diffusion-Autoregressive cloning — preserves more acoustic and emotional detail than token-based models like Qwen3-TTS 💡 Big shoutout to Grok — used your multi-image video magic for our launch demo. It’s scarily good at keeping visuals consistent across shots. Elon Elon Musk, this one’s for you. 😉 Check the demo & start cloning your dream voice: 🌐 Hugging Face Space: 🤗 Hugging Face Model: 🤖 ModelScope Model: 💻 GitHub： #TTS #AI #VoiceCloning #GrokImagine #ElonMusk #OpenBMB #VoxCPM
1:26

🚀 VoxCPM 2 is live! 🎉 Another open-source AI #TTS model from China — and one that stands shoulder to shoulder with Qwen3-TTS, while bringing everything into a single unified model. After rapid iterations from V1 (zero-shot cloning) to V1.5 (long-form + fine-tuning), #VoxCPM has consistently pushed quality and usability forward. Now, VoxCPM 2 takes it further: 🔹30+ languages — truly global, truly local. 🔹Infinite voice design — type it, hear it, control it. From a whisper to a booming cinematic voice. 🔹Studio-grade audio — 48kHz ultra-high fidelity with emotional depth 🔹Diffusion-Autoregressive cloning — preserves more acoustic and emotional detail than token-based models like Qwen3-TTS 💡 Big shoutout to Grok — used your multi-image video magic for our launch demo. It’s scarily good at keeping visuals consistent across shots. Elon Elon Musk, this one’s for you. 😉 Check the demo & start cloning your dream voice: 🌐 Hugging Face Space: 🤗 Hugging Face Model: 🤖 ModelScope Model: 💻 GitHub： #TTS #AI #VoiceCloning #GrokImagine #ElonMusk #OpenBMB #VoxCPM

OpenBMB

558,740 просмотров • 3 месяцев назад

i gave a voice to my jarvis system everything running in real-time using open source models - roboflow RF-DETR for object detection - gemma 4 for scene summarization - kokoro text-to-speech - live in the browser using transformers js prompt: "you are a dystopian science fiction narrator in a cyberpunk world. describe the scene in one sentence"
0:24

i gave a voice to my jarvis system everything running in real-time using open source models - roboflow RF-DETR for object detection - gemma 4 for scene summarization - kokoro text-to-speech - live in the browser using transformers js prompt: "you are a dystopian science fiction narrator in a cyberpunk world. describe the scene in one sentence"

AA

28,731 просмотров • 3 месяцев назад

Blender AI Motion Plugin — a 1-billion-parameter motion model trained on NVIDIA CUDA, running locally in real time with 8GB of VRAM. It converts webcam or video footage into real-time XYZ skeletal point data and rotation values, transmitting them to Blender, Unity, and UE for retargeting.
0:39

Blender AI Motion Plugin — a 1-billion-parameter motion model trained on NVIDIA CUDA, running locally in real time with 8GB of VRAM. It converts webcam or video footage into real-time XYZ skeletal point data and rotation values, transmitting them to Blender, Unity, and UE for retargeting.

CYANPUPPETS

124,866 просмотров • 7 месяцев назад

Blender AI Motion Plugin — a 1-billion-parameter motion model trained on NVIDIA CUDA, running locally in real time with 8GB of VRAM. It converts webcam or video footage into real-time XYZ skeletal point data and rotation values, transmitting them to Blender, Unity, and UE for retargeting.
0:30

Blender AI Motion Plugin — a 1-billion-parameter motion model trained on NVIDIA CUDA, running locally in real time with 8GB of VRAM. It converts webcam or video footage into real-time XYZ skeletal point data and rotation values, transmitting them to Blender, Unity, and UE for retargeting.

CYANPUPPETS

18,317 просмотров • 7 месяцев назад

Blender AI Motion Plugin — a 1-billion-parameter motion model trained on NVIDIA CUDA, running locally in real time with 8GB of VRAM. It converts webcam or video footage into real-time XYZ skeletal point data and rotation values, transmitting them to Blender, Unity, and UE for retargeting.
0:32

Blender AI Motion Plugin — a 1-billion-parameter motion model trained on NVIDIA CUDA, running locally in real time with 8GB of VRAM. It converts webcam or video footage into real-time XYZ skeletal point data and rotation values, transmitting them to Blender, Unity, and UE for retargeting.

CYANPUPPETS

32,379 просмотров • 8 месяцев назад

4. Chan is a trained opera singer. - Chan went to the China Drama Academy where In addition to learning acrobatics and martial arts, he also trained in music and voice and became part of Opera. - Chan continues to embrace his love for singing and the performing arts to this day and has released over 20 albums in multiple languages.
2:25

4. Chan is a trained opera singer. - Chan went to the China Drama Academy where In addition to learning acrobatics and martial arts, he also trained in music and voice and became part of Opera. - Chan continues to embrace his love for singing and the performing arts to this day and has released over 20 albums in multiple languages.

Manifest_Lord

298,966 просмотров • 2 лет назад

🚨BREAKING: Mureka can now make not only full songs but also voiceovers for you V7 gives you vocals + instruments. TTS turns your text into voice with tone and pacing sounds like a real person performing over a real band (🔈on!) workflow below:
1:11

🚨BREAKING: Mureka can now make not only full songs but also voiceovers for you V7 gives you vocals + instruments. TTS turns your text into voice with tone and pacing sounds like a real person performing over a real band (🔈on!) workflow below:

Nelly;

34,768 просмотров • 1 год назад

American doctor put this picture of a very obviously fractured bone into Claude AI and said “Evaluate this X-Ray” The results should horrify you This is why people should not be trusting anything medical to AI, unless they AI has been trained for medical The obvious pushback from people is this AI model probably wasn’t trained for this, well then why is it giving an answer?? It should prompt you that it isn’t trained on this data and it cannot evaluate this
0:53

American doctor put this picture of a very obviously fractured bone into Claude AI and said “Evaluate this X-Ray” The results should horrify you This is why people should not be trusting anything medical to AI, unless they AI has been trained for medical The obvious pushback from people is this AI model probably wasn’t trained for this, well then why is it giving an answer?? It should prompt you that it isn’t trained on this data and it cannot evaluate this

Wall Street Apes

201,636 просмотров • 23 дней назад

Consistent character with Hunyuan and Skyreel! 🎥✨ In collaboration with Kartel.ai .ai, we worked on a pipeline using ComfyUI with the Hunyuan & Skyreel models—both designed for video. We first captured him volumetrically, then trained a LoRA model directly on video data, allowing us to generate sequences where a person remains consistent across shots. The goal is to maintain identity and style over time, pushing the limits of AI-generated video. Excited to explore this further! 🔥 with J. Salvatore in main actor , thank you ! #AI #GenAI #ComfyUI #LoRA #VideoGeneration #Hunyuan #Skyreel
1:28

Consistent character with Hunyuan and Skyreel! 🎥✨ In collaboration with Kartel.ai .ai, we worked on a pipeline using ComfyUI with the Hunyuan & Skyreel models—both designed for video. We first captured him volumetrically, then trained a LoRA model directly on video data, allowing us to generate sequences where a person remains consistent across shots. The goal is to maintain identity and style over time, pushing the limits of AI-generated video. Excited to explore this further! 🔥 with J. Salvatore in main actor , thank you ! #AI #GenAI #ComfyUI #LoRA #VideoGeneration #Hunyuan #Skyreel

Lovis Odin

13,348 просмотров • 1 год назад

And here they do it again… yet another incredible piece of journalism from Sky News Australia. This time by the incredible Sharri Markson. Sharri got to have a one on one with Benjamin Netanyahu - בנימין נתניהו, and this is what she had to say. The difference real honest journalism can make is remarkable. Thank you for your courage and honesty Sharri Markson🩷🩷🩷
3:52

And here they do it again… yet another incredible piece of journalism from Sky News Australia. This time by the incredible Sharri Markson. Sharri got to have a one on one with Benjamin Netanyahu - בנימין נתניהו, and this is what she had to say. The difference real honest journalism can make is remarkable. Thank you for your courage and honesty Sharri Markson🩷🩷🩷

Mor Edge Insight

147,974 просмотров • 1 год назад

Andreas Strassmeir: the most obvious CIA asset of all time. This dude was the son of a politician, trained in counter intel in the German army, went on security patrols w/the IDF, lived w/2 "former" CIA agents, & was kicked out of a militia for being a suspected provocateur. Oh ya, he was also spotted w/Timothy McVeigh multiple times & w/many other individuals also seen w/McVeigh.
0:51

Andreas Strassmeir: the most obvious CIA asset of all time. This dude was the son of a politician, trained in counter intel in the German army, went on security patrols w/the IDF, lived w/2 "former" CIA agents, & was kicked out of a militia for being a suspected provocateur. Oh ya, he was also spotted w/Timothy McVeigh multiple times & w/many other individuals also seen w/McVeigh.

Jose Galison

14,759 просмотров • 1 год назад

@TheRichFromCali this trump? the one who wasn’t scared of a bullet to the head but scared of a bird? yes, absolutely staged. also, the audience just watching and not running away for their lives with an active shooter on the loose? give me a break
0:22

@TheRichFromCali this trump? the one who wasn’t scared of a bullet to the head but scared of a bird? yes, absolutely staged. also, the audience just watching and not running away for their lives with an active shooter on the loose? give me a break

Fahd

39,203 просмотров • 1 год назад

Sean O’Malley Confirms His Teammate Accidentally Leaked His #UFC316 Toe Injury “Suga” Also Mentions He Trained For at least 5 Weeks In Camp With Wrestling Shoes on and Fight Night was the First Time Without Shoes 🤯
0:41

Sean O’Malley Confirms His Teammate Accidentally Leaked His #UFC316 Toe Injury “Suga” Also Mentions He Trained For at least 5 Weeks In Camp With Wrestling Shoes on and Fight Night was the First Time Without Shoes 🤯

Kevin

268,404 просмотров • 11 месяцев назад