Cool release by Liquid AI: LFM2-Audio-1.5B It’s a pretty cool omni-architecture that enables prediction of both text and audio tokens, meaning it can handle multi-turn S2S, ASR, and TTS (with voice description) within a single model. Great to see, once again this year, a model

Just dropped on HF: Treble10, our collab with Treble Technologies, a full-band hybrid dataset for realistic speech & acoustics research: • 3000+ RIRs across 10 complex rooms • Mono, 8th-order Ambisonics & 6-mic array • LibriSpeech speech via hybrid simulations

Here is a minimal ParakeetCTC finetuning repo (with 🤗 Transformers and PEFT).

Let’s meet at PyTorch conf !! #PyTorchCon

Any git power users in my mutuals/ timeline? We have a new and faster git experience coming up on Hugging Face and we'd love to get feedback from you! Comment or DM and I'll hook you up!

big announcement tomorrow. a clue

You can now train SOTA models without any storage!🌩️ We completely revamped the Hub’s backend to enable streaming at scale. We streamed TBs of data to 100s of H100s to train SOTA VLMs and saw serious speed-ups. But how?