Ofcourse. It depends on what do you optimise for SpeechT5 TTS (AR) does sound better than vanilla FastSpeech2 (NAR) however worse than VITS/PortaSpeech. Significantly worse than TorToise TTS. However it is considerably slow.
GENERATIVE AI
-
ChatGPT vs Stockfish Chess Match Prediction
By
–
Some madlad decided to pit ChatGPT against Stockfish, the predominant AI chess engine
— swyx 🐣 (@swyx) 10 février 2023
see if you can tell who’s who, and predict who will win pic.twitter.com/zWGed293VjSome madlad decided to pit ChatGPT against Stockfish, the predominant AI chess engine see if you can tell who’s who, and predict who will win
-
CICERO by Meta AI: Strategic Dialogue Generation Process
By
–
#CICERObyMetaAI generates strategic, free-form dialogue by: Predicting the moves other players are likely to make. Creating a plan based on those predictions. Generating messages. Filtering the final messages for clarity and value. Read more on our blog
-
Stability AI Open-Sources Checkpoints Thanks
By
–
Also Big Thanks to @StabilityAI and @RiversHaveWings for open-sourcing the checkpoints!
-
OpenAI ChatGPT Users Frustrated With Timeout Issues
By
–
I guess everyone gets frustrated with the time-outs… // @OpenAI $MSFT $CHKP // #AI #deeplearning #OpenAI #ChatGPT
-
Beyond generative AI: exploring diverse opportunities in other fields
By
–
Que no os eclipse toda la parte generativa de texto, que también están pasando muchas más cosas interesantes en otros ámbitos 🙂 https://t.co/KfKyCKI8rG
— Carlos Santana (@DotCSV) 10 février 2023Que no os eclipse toda la parte generativa de texto, que también están pasando muchas más cosas interesantes en otros ámbitos 🙂
-
Open-Assistant Project: LAION-AI’s Open Source Initiative
By
–
El proyecto no es ese, es este. https://
github.com/LAION-AI/Open-
Assistant
… -
Hugging Face Diffusers: Pre-trained Diffusion Models for Vision and Audio
By
–
4. Hugging Face Diffusers We are noticing the recent trend with applications using Diffusion Models either it can be Stable Diffusion or Dalle E Diffusers library provide you with pre trained diffusion models across vision and audio. Check this: https://
github.com/huggingface/di
ffusers
… -
New AI model twice faster than ChatGPT after initial search
By
–
Más rápido es. Tarda un poco más al inicio, que usa para buscar información de Internet, y luego va a un x2 de lo que tarda en generar ChatGPT.
-
GPT-4 Cost Viability and OpenAI’s Embedding Price Strategy
By
–
El costo de GPT-4 es algo que me ha tenido estos días pensando sobre la viabilidad de meterlo en un buscador. Pero dándole una vuelta, he recordado lo que hizo OpenAI en Diciembre, mejorando sus modelos de Embeddings a la par que reduciendo su precio un 99.8% !!! Da que pensar.