Hugging Face's logo
Alibaba_Speech_Lab_SG's picture
4 8

Alibaba_Speech_Lab_SG PRO

alibabasglab
yaoxunji's profile picture Krishna1337's profile picture jhauret's profile picture
·

AI & ML interests

speech enhancement, separation, and codec

Recent Activity

posted an update 8 days ago
Do you need to improve your speech audio to premium quality? If so, please try out our latest open-sourced free speech processing toolkit: [ClearerVoice-Studio](https://github.com/modelscope/ClearerVoice-Studio)! Check out our live demo at https://huggingface.co/spaces/alibabasglab/ClearVoice and https://modelscope.cn/studios/iic/ClearerVoice-Studio.
posted an update 13 days ago
ClearerVoice-Studio: your one-step speech processing platform for speech enhancement, speech separation, speech super-resolution, and audio-visual target speaker extraction. Say goodbye to noise and hello to clarity! Online demo: https://huggingface.co/spaces/alibabasglab/ClearVoice . Github repo: https://github.com/modelscope/ClearerVoice-Studio
new activity 14 days ago
alibabasglab/MossFormer2_SR_48K:Update README.md
View all activity

Organizations

Alibaba-PAI's profile picture

alibabasglab's activity

posted an update 8 days ago
posted an update 13 days ago
New activity in alibabasglab/MossFormer2_SR_48K 14 days ago

Update README.md
#1 opened 15 days ago by
Pur1zumu
New activity in alibabasglab/LJSpeech-1.1-48kHz 14 days ago

Add task category, link to paper
#2 opened 14 days ago by
nielsr
updated a model 14 days ago
updated a dataset 14 days ago
updated a Space 14 days ago
reacted to their post with 🤗❤️🚀🔥 15 days ago
posted an update 15 days ago
reacted to their post with 🤝❤️🔥 18 days ago
reacted to prithivMLmods's post with 🔥 18 days ago
view post
Post
3074
ChemQwen-vL [ Qwen for Chem Vision ] 🧑🏻‍🔬

🧪Model : prithivMLmods/ChemQwen-vL

📝ChemQwen-vL is a vision-language model fine-tuned based on the Qwen2VL-2B Instruct model. It has been trained using the International Chemical Identifier (InChI) format for chemical compounds and is optimized for chemical compound identification. The model excels at generating the InChI and providing descriptions of chemical compounds based on their images. Its architecture operates within a multi-modal framework, combining image-text-text capabilities. It has been fine-tuned using datasets from: https://iupac.org/projects/

📒Colab Demo: https://tinyurl.com/2pn8x6u7, Collection : https://tinyurl.com/2mt5bjju

Inference with the documentation is possible with the help of the ReportLab library. https://pypi.org/project/reportlab/

🤗: @prithivMLmods
  • 1 reply
·
replied to prithivMLmods's post 18 days ago
reacted to m-ric's post with 👀 18 days ago
view post
Post
1214
𝗠𝗶𝗻𝗶𝗠𝗮𝘅'𝘀 𝗻𝗲𝘄 𝗠𝗼𝗘 𝗟𝗟𝗠 𝗿𝗲𝗮𝗰𝗵𝗲𝘀 𝗖𝗹𝗮𝘂𝗱𝗲-𝗦𝗼𝗻𝗻𝗲𝘁 𝗹𝗲𝘃𝗲𝗹 𝘄𝗶𝘁𝗵 𝟰𝗠 𝘁𝗼𝗸𝗲𝗻𝘀 𝗰𝗼𝗻𝘁𝗲𝘅𝘁 𝗹𝗲𝗻𝗴𝘁𝗵 💥

This work from Chinese startup @MiniMax-AI introduces a novel architecture that achieves state-of-the-art performance while handling context windows up to 4 million tokens - roughly 20x longer than current models. The key was combining lightning attention, mixture of experts (MoE), and a careful hybrid approach.

𝗞𝗲𝘆 𝗶𝗻𝘀𝗶𝗴𝗵𝘁𝘀:

🏗️ MoE with novel hybrid attention:
‣ Mixture of Experts with 456B total parameters (45.9B activated per token)
‣ Combines Lightning attention (linear complexity) for most layers and traditional softmax attention every 8 layers

🏆 Outperforms leading models across benchmarks while offering vastly longer context:
‣ Competitive with GPT-4/Claude-3.5-Sonnet on most tasks
‣ Can efficiently handle 4M token contexts (vs 256K for most other LLMs)

🔬 Technical innovations enable efficient scaling:
‣ Novel expert parallel and tensor parallel strategies cut communication overhead in half
‣ Improved linear attention sequence parallelism, multi-level padding and other optimizations achieve 75% GPU utilization (that's really high, generally utilization is around 50%)

🎯 Thorough training strategy:
‣ Careful data curation and quality control by using a smaller preliminary version of their LLM as a judge!

Overall, not only is the model impressive, but the technical paper is also really interesting! 📝
It has lots of insights including a great comparison showing how a 2B MoE (24B total) far outperforms a 7B model for the same amount of FLOPs.

Read it in full here 👉 MiniMax-01: Scaling Foundation Models with Lightning Attention (2501.08313)
Model here, allows commercial use <100M monthly users 👉 MiniMaxAI/MiniMax-Text-01
reacted to Tonic's post with 🔥 18 days ago
view post
Post
1821
🙋🏻‍♂️ Hey there folks ,

Facebook AI just released JASCO models that make music stems .

you can try it out here : Tonic/audiocraft

hope you like it
reacted to ariG23498's post with 🚀 18 days ago