view post Post 4040 AI will bring us "a country of yes-men on servers" instead of one of "Einsteins sitting in a data center" if we continue on current trends.Must-read by @thomwolf deflating overblown AI promises and explaining what real scientific breakthroughs require.https://thomwolf.io/blog/scientific-ai.html See translation 2 replies ยท โค๏ธ 8 8 ๐ 7 7 ๐ฅ 4 4 ๐ 1 1 + Reply
Running on Zero 6 6 Llasa 1B Finetuned For Two Speakers ๐ฅ Using dataset shb777/gemini-flash-2.0-speech for finetuning
Running on CPU Upgrade 1.9k 1.9k Stable Diffusion XL on TPUv5e ๐ Generate images from text prompts with various styles
Running on TPU v5e 142 142 Whisper JAX ๐ Transcribe or translate audio from microphone, file, or YouTube
view post Post 8414 hexgrad/Kokoro-82M got an upgrade! โฌ๏ธ More voices, more languages, pip install kokoro, and still 82M parameters.GitHub: https://github.com/hexgrad/kokoroPyPI: https://pypi.org/project/kokoro/Space: hexgrad/Kokoro-TTS See translation 11 replies ยท ๐ฅ 29 29 โค๏ธ 10 10 ๐ 10 10 ๐ 3 3 ๐ค 1 1 + Reply
view reply It looks like your config set temperature to 0 , it should be 0.6 according to Usage Recommendations
view article Article Train 400x faster Static Embedding Models with Sentence Transformers Jan 15 โข 159