Mostly hoping for MiniOmni 2 and likes to get better before putting time into production pipelines for them
@reach_vb
-
Choosing TTS Engines for Lightweight GPU Hardware Deployment
By
–
It depends on the hardware you choose to deploy the TTS engine. For lightweight GPUs I’d recommend using MeloTTS
-
AI Voice Synthesis: Reference Speaker Audio Persona Replication
By
–
You just pass a reference speaker audio and it synthesises audio in that persona.
-
Scraping Permissive Data for Better AI Training
By
–
Agreed! Time to scrape permissive and better data
-
Real-time API implementation deployable on L4 under one dollar
By
–
Emphasis on cascaded. We do have real-time API based implementation which you can deploy on a L4 at less than 1$ an hour.
-
Hugging Chat: Exploring Open Source AI Conversational Platform
By
–
That’s great, have you heard about http://
hugging.chat -
Two Open Text-to-Speech Models Challenge ElevenLabs Monthly
By
–
That's two open Text to Speech models in the same month that are in the same arena as ElevenLabs!
— Vaibhav (VB) Srivastav (@reach_vb) 30 octobre 2024
Slowly, then suddenly! https://t.co/vvYkTFnGHq pic.twitter.com/0IMRP8KDRqThat's two open Text to Speech models in the same month that are in the same arena as ElevenLabs! Slowly, then suddenly!
-
MaskGCT Open Source Text-to-Speech Model Achieves New SoTA
By
–
Fuck yeah! MaskGCT – New open SoTA Text to Speech model! 🔥
— Vaibhav (VB) Srivastav (@reach_vb) 30 octobre 2024
> Zero-shot voice cloning
> Emotional TTS
> Trained on 100K hours of data
> Long form synthesis
> Variable speed synthesis
> Bilingual – Chinese & English
> Available on Hugging Face
Fully non-autoregressive… pic.twitter.com/CAUX6cTiAGFuck yeah! MaskGCT – New open SoTA Text to Speech model! > Zero-shot voice cloning
> Emotional TTS
> Trained on 100K hours of data
> Long form synthesis
> Variable speed synthesis
> Bilingual – Chinese & English
> Available on Hugging Face Fully non-autoregressive -
Hugging Face Hub acquisition: legendary team and tool integration
By
–
Has to go down the history books! What a legendary team and acquisition! Coincidentally, outside of transformers my real entry point to HF Hub was through spaces and Gradio. Still remember the feeling of putting together a nicely packaged demo in less than 7 lines of code.