Hacker News with Generative AI: Language Modeling

Jargonic: Industry-Tunable ASR Model (aiola.ai)
Automatic Speech Recognition (ASR) has made significant strides over the last decade, but most ASR models on the market offer general-purpose transcription. They perform well in clean, controlled environments but break down when handling:
Artificial Intelligence, Machine Learning, Language Modeling
55 points by agold97 22 hours ago | 7 comments
A CC-By Open-Source TTS Model with Voice Cloning (huggingface.co)
OuteTTS-0.1-350M is a novel text-to-speech synthesis model that leverages pure language modeling without external adapters or complex architectures, built upon the LLaMa architecture using our Oute3-350M-DEV base model, it demonstrates that high-quality speech synthesis is achievable through a straightforward approach using crafted prompts and audio tokens.
Open Source, Text-to-Speech, Voice Cloning, AI, Language Modeling
131 points by amrrs 149 days ago | 31 comments
Have we stopped to think about what LLMs model? (theregister.com)
Artificial Intelligence, Language Modeling
20 points by LinuxBender 213 days ago | 32 comments