65
InspireMusic
๐ถ
Music Generation - text to music, music continuation.
Alibaba_Speech_Lab_SG PRO
alibabasglab
AI & ML interests
speech enhancement, separation, and codec
Recent Activity
liked
a Space
3 days ago
FunAudioLLM/InspireMusic
posted
an
update
about 1 month 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
about 1 month 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
Organizations
alibabasglab's activity
liked
a
Space
3 days ago
posted
an
update
about 1 month ago
Post
2285
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
alibabasglab/ClearVoice
and https://modelscope.cn/studios/iic/ClearerVoice-Studio.
and https://modelscope.cn/studios/iic/ClearerVoice-Studio.
- 1 reply
posted
an
update
about 1 month ago
Post
2061
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: alibabasglab/ClearVoice .
Github repo: https://github.com/modelscope/ClearerVoice-Studio
Online demo: alibabasglab/ClearVoice .
Github repo: https://github.com/modelscope/ClearerVoice-Studio
Update README.md
#1 opened about 2 months ago
by
Pur1zumu
Add task category, link to paper
#2 opened about 1 month ago
by
nielsr
updated
a
model
about 1 month ago
updated
a
dataset
about 1 month ago
updated
a
Space
about 1 month ago
reacted to
their
post with ๐คโค๏ธ๐๐ฅ
about 2 months ago
Post
1703
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
alibabasglab/ClearVoice
and https://modelscope.cn/studios/iic/ClearerVoice-Studio.
and https://modelscope.cn/studios/iic/ClearerVoice-Studio.
posted
an
update
about 2 months ago
Post
1703
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
alibabasglab/ClearVoice
and https://modelscope.cn/studios/iic/ClearerVoice-Studio.
and https://modelscope.cn/studios/iic/ClearerVoice-Studio.
reacted to
their
post with ๐คโค๏ธ๐ฅ
about 2 months ago
Post
1223
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!
reacted to
prithivMLmods's
post with ๐ฅ
about 2 months ago
Post
3144
ChemQwen-vL [ Qwen for Chem Vision ] ๐ง๐ปโ๐ฌ
๐งชModel : prithivMLmods/ChemQwen-vL
๐ChemQwen-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/
๐Colab 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/
๐ค: @prithivMLmods
๐งชModel : prithivMLmods/ChemQwen-vL
๐ChemQwen-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/
๐Colab 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/
๐ค: @prithivMLmods
-
- 1 reply
replied to
prithivMLmods's
post
about 2 months ago
Nice work!
reacted to
m-ric's
post with ๐
about 2 months ago
Post
1373
๐ ๐ถ๐ป๐ถ๐ ๐ฎ๐
'๐ ๐ป๐ฒ๐ ๐ ๐ผ๐ ๐๐๐ ๐ฟ๐ฒ๐ฎ๐ฐ๐ต๐ฒ๐ ๐๐น๐ฎ๐๐ฑ๐ฒ-๐ฆ๐ผ๐ป๐ป๐ฒ๐ ๐น๐ฒ๐๐ฒ๐น ๐๐ถ๐๐ต ๐ฐ๐ ๐๐ผ๐ธ๐ฒ๐ป๐ ๐ฐ๐ผ๐ป๐๐ฒ๐
๐ ๐น๐ฒ๐ป๐ด๐๐ต ๐ฅ
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.
๐๐ฒ๐ ๐ถ๐ป๐๐ถ๐ด๐ต๐๐:
๐๏ธ MoE with novel hybrid attention:
โฃ Mixture of Experts with 456B total parameters (45.9B activated per token)
โฃ Combines Lightning attention (linear complexity) for most layers and traditional softmax attention every 8 layers
๐ Outperforms leading models across benchmarks while offering vastly longer context:
โฃ Competitive with GPT-4/Claude-3.5-Sonnet on most tasks
โฃ Can efficiently handle 4M token contexts (vs 256K for most other LLMs)
๐ฌ Technical innovations enable efficient scaling:
โฃ Novel expert parallel and tensor parallel strategies cut communication overhead in half
โฃ Improved linear attention sequence parallelism, multi-level padding and other optimizations achieve 75% GPU utilization (that's really high, generally utilization is around 50%)
๐ฏ Thorough training strategy:
โฃ 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! ๐
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 ๐ MiniMax-01: Scaling Foundation Models with Lightning Attention (2501.08313)
Model here, allows commercial use <100M monthly users ๐ MiniMaxAI/MiniMax-Text-01
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.
๐๐ฒ๐ ๐ถ๐ป๐๐ถ๐ด๐ต๐๐:
๐๏ธ MoE with novel hybrid attention:
โฃ Mixture of Experts with 456B total parameters (45.9B activated per token)
โฃ Combines Lightning attention (linear complexity) for most layers and traditional softmax attention every 8 layers
๐ Outperforms leading models across benchmarks while offering vastly longer context:
โฃ Competitive with GPT-4/Claude-3.5-Sonnet on most tasks
โฃ Can efficiently handle 4M token contexts (vs 256K for most other LLMs)
๐ฌ Technical innovations enable efficient scaling:
โฃ Novel expert parallel and tensor parallel strategies cut communication overhead in half
โฃ Improved linear attention sequence parallelism, multi-level padding and other optimizations achieve 75% GPU utilization (that's really high, generally utilization is around 50%)
๐ฏ Thorough training strategy:
โฃ 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! ๐
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 ๐ MiniMax-01: Scaling Foundation Models with Lightning Attention (2501.08313)
Model here, allows commercial use <100M monthly users ๐ MiniMaxAI/MiniMax-Text-01
reacted to
Tonic's
post with ๐ฅ
about 2 months ago
Post
1881
๐๐ปโโ๏ธ 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
Facebook AI just released JASCO models that make music stems .
you can try it out here : Tonic/audiocraft
hope you like it