Martin Viewegger

Viewegger's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

reacted to alibabasglab's post with 👍 about 22 hours ago

view post

Post

531

Introducing open-sourced ClearerVoice-Studio. A powerful speech processing AI tool to dramatically improve your speech quality. Checkout demo page: alibabasglab/ClearVoice and https://modelscope.cn/studios/iic/ClearerVoice-Studio. Give us a Star on Github: https://github.com/modelscope/ClearerVoice-Studio!

See translation

• 
• 
• 

🚀

4

4

👍

3

3

🔥

2

2

❤️

2

2

🤝

2

2

+

Reply

reacted to alibabasglab's post with 👍 5 days ago

view post

Post

5226

🎉 ClearerVoice-Studio New Feature: Speech Super-Resolution with MossFormer2 ! 🚀
We’re excited to announce that ClearerVoice-Studio now supports speech super-resolution, powered by our latest MossFormer2-based model!
What’s New?

🔊 Convert Low-Resolution to High-Resolution Audio:
Transform low-resolution audio (effective sampling rate ≥ 16 kHz) into crystal-clear, high-resolution audio at 48 kHz.

🤖 Cutting-Edge Technology:
Leverages the MossFormer2 model plus HiFi-GAN, optimised for generating high-quality audio with enhanced perceptual clarity.

🎧 Enhanced Listening Experience:
Perfect for speech enhancement, content restoration, and high-fidelity audio applications.

🌟 Try It Out!
Upgrade to the latest version of ClearerVoice-Studio (https://github.com/modelscope/ClearerVoice-Studio) to experience this powerful feature. Check out the updated documentation and examples in our repository.

Let us know your thoughts, feedback, or feature requests in the Issues section.

See translation

👍

11

11

👀

2

2

+

Reply

liked a model 13 days ago

hexgrad/Kokoro-82M

Text-to-Speech • Updated about 10 hours ago • 22.6k • 1.9k

liked 2 models 29 days ago

strangerzonehf/Flux-C7-Sketch-LoRA

Text-to-Image • Updated 29 days ago • 126 • • 10

strangerzonehf/Flux-Sketch-Smudge-LoRA

Text-to-Image • Updated 29 days ago • 9.14k • • 29

New activity in tensorart/stable-diffusion-3.5-medium-turbo 29 days ago

Benefit using Lora + finetuned model

1

#1 opened 29 days ago by

Viewegger

liked 2 models about 2 months ago

unsloth/Qwen2.5-Coder-32B-Instruct-128K-GGUF

Updated Nov 15, 2024 • 9.95k • 55

NexaAIDev/OmniVLM-968M

Updated Dec 17, 2024 • 1.16k • 496

New activity in jpgallegoar/F5-Spanish about 2 months ago

Model quality on cca 200hour of audio

2

#8 opened about 2 months ago by

Viewegger

New activity in PetrosStav/F5-TTS-Greek about 2 months ago

Dataset size and output quality

#2 opened about 2 months ago by

Viewegger

New activity in marduk-ra/F5-TTS-German about 2 months ago

Training process details

4

#2 opened about 2 months ago by

Nils11

liked a Space 2 months ago

Running

394

👁

Qwen2.5 Coder Demo

reacted to m-ric's post with 🔥 2 months ago

view post

Post

789

𝗔𝗿𝗲 𝘀𝗰𝗮𝗹𝗶𝗻𝗴 𝗹𝗮𝘄𝘀 𝗼𝘃𝗲𝗿? 𝗔 𝗿𝗲𝗽𝗼𝗿𝘁 𝗳𝗿𝗼𝗺 𝘁𝗵𝗲 𝗜𝗻𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝗼𝗻 𝗮𝗻𝗻𝗼𝘂𝗻𝗰𝗲𝗱 𝘁𝗵𝗮𝘁 𝗢𝗽𝗲𝗻𝗔𝗜 𝗶𝘀 𝘀𝗲𝗲𝗶𝗻𝗴 𝗱𝗶𝗺𝗶𝗻𝗶𝘀𝗵𝗶𝗻𝗴 𝗿𝗲𝘁𝘂𝗿𝗻𝘀 𝗳𝗿𝗼𝗺 𝘀𝗰𝗮𝗹𝗶𝗻𝗴 𝘂𝗽 𝘁𝗵𝗲 𝗻𝗲𝘅𝘁 𝗚𝗣𝗧 𝗺𝗼𝗱𝗲𝗹𝘀.

📊 What are scaling laws? These are empiric laws that say "Every time you increase compute spent in training 10-fold, your LLM's performance will go up by a predictable tick". Of course, they apply only if you train your model with the right methods.

The image below illustrates it: they're from a paper by Google, "Scaling Autoregressive Models for Content-Rich Text-to-Image Generation", and they show how quality and instruction following of models improve when you scale the model up (which is equivalent to scaling up the compute spent in training).

➡️ These scaling laws have immense impact: they triggered the largest gold rush ever, with companies pouring billions into scaling up theiur training. Microsoft and OpenAI spent 100B into their "Startgate" mega training cluster, due to start running in 2028.

🤔 So, what about these reports of scaling laws slowing down?

If they are true, they would mean a gigantic paradigm shift, as the hundreds of billions poured by AI companies into scaling could be a dead-end. ⛔️

But I doubt it: until the most recent publications, scaling laws showed no signs of weakness, and the researchers at the higher end of the scale-up seems to imply the scaling up continues.

Wait and see!

• 

• 
• 1 reply

·

🔥

2

2

👀

1

1

+

Reply

liked a model 2 months ago

prithivMLmods/SD3.5-Large-Photorealistic-LoRA

Text-to-Image • Updated Nov 16, 2024 • 8.38k • • 52

upvoted a paper 3 months ago

NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks

Paper • 2410.20650 • Published Oct 28, 2024 • 16

reacted to yongchanghao's post with 🔥 3 months ago

view post

Post

3756

We just released a paper (NeuZip) that compresses VRAM in a lossless manner to run larger models. This should be particularly useful when VRAM is insufficient during training/inference. Specifically, we look inside each floating number and find that the exponents are highly compressible (as shown in the figure below).

Read more about the work at NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks (2410.20650)

• 

🔥

18

18

👀

3

3

+

Reply

liked a dataset 3 months ago

ai4b-hf/GLOBE-annotated

Viewer • Updated Oct 31, 2024 • 582k • 343 • 3

New activity in gokaygokay/Flux-Seamless-Texture-LoRA 3 months ago

Size of the dataset?

8

#1 opened 3 months ago by

Viewegger

liked 2 models 3 months ago

Ertugrul/Pixtral-12B-Captioner-Relaxed

Image-to-Text • Updated Oct 1, 2024 • 148 • 18

SeanScripts/pixtral-12b-nf4

Image-Text-to-Text • Updated Sep 26, 2024 • 574 • 20