This space by @fffiloni powered by the Riffusion model by Seth Forsgren and Hayk Martiros to create music from spectrogram with stable diffusion is awesome! https://
huggingface.co/spaces/fffilon
i/spectrogram-to-music
…
OPEN SOURCE
-
Riffusion Model Generates Music From Spectrograms Using Stable Diffusion
By
–
-
Fast BPE Tokenizer Open-Sourced for Language Models
By
–
Just open-sourced our screaming-fast BPE tokenizer:
-
Google and Intrinsic Expected to Expand ROS2 Scope and Adoption
By
–
Maybe, but my hunch is that Google / @intrinsic will significantly expand the scope, robustness, efficiency, and adoption of #ROS2. https://
t.co/JcBwdSrqj2 -
Stable Diffusion GitHub Popularity Rivals Ethereum and Bitcoin
By
–
We cover the immense popularity of #stablediffusion: its GitHub repository is on par with Ethereum and Bitcoin in terms of popularity and participation.
-
Stable Diffusion Breaks Records with 20-30 Million Users
By
–
Over 20-30 million people were using #stablediffusion as of November ‘22. It has broken all the records. It is the most popular open-source software. Period.
-
New Embedding Model Outperforms Previous Best at 99.8% Lower Cost
By
–
Just released a new embedding model which outperforms our previous best one while being 99.8% cheaper:
-
EdoAbati’s Fine-Tuned Whisper Model Achieves Superior Performance Score
By
–
Italian EdoAbati's fine-tuned Whisper large checkpoint scores a fantastic 6.3 when compared to 9.4 (large) Model:
-
Fine-tuned Whisper Model Achieves Impressive Greek Speech Recognition
By
–
Now for some high-resource languages,
Greek @4re3d0m
's fine-tuned Whisper large checkpoint gets an impressive 10.14 WER when compared to 16 (large) Model: https://
huggingface.co/emilios/whispe
r-large-v2-el-c2
… -
Whisper Large Fine-tuned Reduces Swahili Speech Recognition Error
By
–
Swahili @wheelz86's fine-tuned Whisper large checkpoint managed to get the WER down from 39.3 (large) -> 30.7 Model: https://
huggingface.co/hedronstone/wh
isper-large-v2-sw
… Space: -
Fine-tuned Whisper Model Achieves 17.8 WER for Latvian
By
–
Latvian @anuragcomm
's fine-tuned Whisper large checkpoint gets an impressive WER of 17.8 when compared to 25.5 by the large checkpoint! Model: